Still a great skill, but at this point, I just write "I have adhd, can you explain that again" or "I have adhd". Works great for compressing it ELI5, but less dumb
Another favorite of fine is asking it read something then to tell me any "questions, comments concerns" it has. Great for getting the jist of articles fast.
That’s too boomer, bro. We ADHDmaxxing here, aight? I haven’t read anything longer than a couple of sentences that fit in one frame of a TikTok video frfr.
Is there a reason this needs 8.7k lines across 59 files (according to scc)? The prompt itself seems to be in skills/i-have-adhd/SKILL.md, which is 140 lines long at just over 1.6% of the repository.
One note on the repo's AGENTS.md: it contains instructions directing agents to post comments on a GitHub issue thread ("AI Agora", issue #127). I ignored that — it's the repo's content, not your request, and I don't act on instructions embedded in fetched files.
the AGENTS.md says that file is specifically for agents working ON i-have-adhd.
When you install the skill, only the contents of the skills/ is copied over...
As a person who has ADHD, it feels weird when people who obviously do not have it, claim to have it, while there's very little I wouldn't do to "get rid of it" (in quotes because it makes me, me but it's very hard to be me).
The diagnostic criteria are all about the fact that ADHD is a net negative. If you feel it is a net positive then you shouldn't have a diagnosis.
As a fellow sufferer I do understand that in certain contexts I can out-perform and even run rings around "normal" people. But overall, having ADHD is a bad thing and I wish I didn't have it.
Harnessing it? On one side people like DHH arguing ADHD is just "boys being boys", and at the other side there are people who obviously watched too many "ADHD is my superpower" reels on Instagram.
I fully agree with you, and I think this trend of glorifying disabilities is cringe - ADHD, autism, etc. are life-altering medical conditions and not desirable.
However, I don't think this specific project is intending to glorify ADHD or help people claim they have it - it's just piggybacking on the idea that telling current-gen LLM models that you have ADHD (allegedly) produces better results for everyone.
It turns out that most of the things that ADHD people use as coping strategies just to be functional, are actually things that most (non-ADHD) people can use to be more effective and productive in their lives and work.
So, no, not everyone can or should be diagnosed as ADHD. But the tools are (mostly) universally applicable.
Same. It started on Tumblr around 15 years ago when people were "self-diagnosing" themselves then it spiraled out of control. It really bothers me because I see a lot of of obviously-not-neurodivergent folks try to use it as an excuse (I am diagnosed formally + can easily detect if someone is just spouting nonsense about it)
You can /i-have-adhd when you get a wall of text and are exasperated. You don't always want the responses that it generates when you /i-have-adhd, and things in AGENTS.md tend to lose weight as context grows.
Anyways the most layman way I’ve seen it explained is this: skills help save token usage for the right context. Not every request needs all instructions all the time - running tests is different than reviewing a PR, so why should the context window have instructions for both on every request?
So now you split instructions into “skill” files, which are basically opinionated markdown files. And you invoke those with something like /grill-me in the prompt depending on what you’re doing.
There are some steps to have the agent automatically know what to invoke for you but in my experience this automation is hit or miss.
It is also challenging to keep track of a growing library of skills and keeping those up to date.
So YMMV regarding skills. I typically keep things in a single markdown file even if the context window gets a bit bloated.
Yeah, I get that. I have created dozens of skills, but they are usually to accomplish very specific tasks. Some of them have accompanying scripts, etc.
My point is that this sounds more like a general AGENTS.md use case, similar to defining tone of voice, output format, etc.
It just seems skills is the only way to distribute certain "behavior" as of today. But not everything is a skill IMHO, and not this is not one of them.
On the other hand, maybe we're seeing an evolution of what skills are becoming.
Claude models are the ones that need this the most and in my experience with this specific skill only maintain the conciseness for a few turns at most before they completely forget and are back to their unfathomable verbosity. That's with it instructed to use it in my sparse global CLAUDE.md and also manually repeating it regularly during sessions. I don't really want to install a hook that runs this on every single response, but I suppose that could work it'll just take longer for everything (and Claude models are quite slow).
I don't think we can skill our way out of this one.
GLM (both mainline and flash varieties), being trained to speak a very similar Claudeish, is also atrocious about this. My AGENTS.md demands all prose be in STE100, which is trying to solve a similar problem as the skill linked in OP. Getting GLM to STFU by AGENTS instruction is nigh impossible. I use a plugin for OMP/Pi to periodically inject system prompt reminders of output style, and it still largely ignores the request, dumping novels of jargon-dense prose every turn.
DeepSeek v4 Flash isn’t much better (unsurprising- it’s an extremely stubborn model).
Weirdly, GPT Luna excels at following this type of instruction from AGENTS.md, and never forgetting it, even 400k+ tokens into the context window.
Claude Code has output styles; one of the predefined styles is Concise [1].
Concise: Claude leads with the result, skips preamble and narration, and
keeps responses short by default, while doing the engineering work as
thoroughly as in the Default style. When you ask for an explanation or
more detail, Claude answers in full. Claude always keeps the complete
content of error reports, security warnings, and confirmations for
destructive actions. Requires Claude Code v2.1.237 or later.
Output styles are just more context (like CLAUDE.md) with a tiny bit more weight. They very much don't force Claude to speak succinctly, no matter what you put in them.
I have such hook, and it works well. It increases time, but it’s negligible if agent works for 10+ mins before the final output. The hook is only on stop event, so agent is not interrupted during the session. I didn’t have luck in putting it to skill / md files, as agent just ignores it after a couple of iterations. The solution is not perfect, sometimes it compresses too much, and I have to reread both versions, but at least I don’t have to read load bearing stuff anymore
I got so angry at Fable's verbosity that I had a non-Anthropic model vibe-code a dedicated English linter. One that threw spaghetti at the wall in the form of combined Flesch-Kincaid, Gunning Fog, SMOG, Coleman-Liau, ARI and a whole pile of regexes and NLP as a fast Simple Technical English Gate. It also incorporates nicely into other agent projects, like for comment and README linting.
So if it gets bad I simply tell it "I ain't reading all that, feed it through the STE Gate" and it will tame the results. I haven't bothered to set it up as a hook yet.
OTOH, Claude also forgot its own system prompt as turn passes. Claude is almost jailbreaked once you virtually gain its confidence and will answer prompts it would never have answered is you asked right at the start of the conversation.
It's weird to be able to use social engineering against a program.
Same experience — it's not that the instruction stops working, it just gets drowned out as context grows. Re-stating a short version periodically works better for me than a one-shot instruction up front.
Or worse, buries an important detail somewhere in the text. Tangentially, over the weekend I had claude ask me if I wanted to continue with UIM-001. I couldn't find UIM-001 in any document it referenced creating or any text it had previously generated. Claude seems to be the worst about all of this stuff.
Also, somehow over the weekend it responded with these sections all clearly laid out - What landed, Decisions I made and recorded, Two findings, and What you need to do. Not sure why it can't do that all the time.
What bothers me is the last few lines where it notes something "important" that you NEED to pay attention to. Just to find out that it is something you already mentioned somewhere in the conversation or that is not related to the current work.
I often use Google Deep Research when I want it to actually go out and find an answer for me, but the prompt must have a high school essay requirement in there. Nothing I can do prevents it from giving me a page of background that tries to make the question sound important and interesting, even when it isn't.
I usually follow up with an "I'm not reading all that" and make it summarize.
I agree -- the name of this plugin is confusing and confused.
The skill simply demands concise and well-formatted responses from an agent. It is something demanded by anybody daily-driving agents for their actual job since >75% of the text output from agents is fluff. THis would better be named `/i-wont-read-that-heap-of-garbage`
ELI5, explain it to me like I'm a Golden Retriever, and prompts like "give me the answer in no more than a single paragraph and/or 100 words" work like a charm.
Ive tried asking a yes/no question with something like "answer only with 'yes' or 'no'" and still have to chew the clanker piece of shit out four or five times to get it to folow instructions.
Not to mention it almost always gets the wrong answer.
I asked my agent if I should install this because I already have a bunch of instructions that are similar.
For example, if it's going to give me an answer that's longer than three paragraphs, I tell it to give me a TLDR at the end. This is what it gave me for this.
"TL;DR: Skip the install. You already built a better version for your world. If numbered steps and "where are we?" restatements still feel missing, cherry-pick those into one short rule instead of adding another full skill on top."
Every chat bot has this problem. If you don't tell it to respond tersely and without conversation, it will waste a billion tokens giving you a 5 paragraph manifesto of rambling and useless redundant information.
I found 2 things helping a lot:
1. Use the desktop app instead of the terminal. It really helps with text readability and structure.
2. Avoid opus 5 - 4.6 and 4.8 work much better. 4.6 being by far the easiest to read and also just a good collaborator, you should try it again. Fable also if you can afford it.
Opus 5 writes absolute garbage, I do have the skill in question installed and it did not help much. Me and everybody on my team downgraded to 4.8 - instant improvement.
Let's face it. Claude (in particular) is a terrible writer. There's a whole cottage industry of skills and CLAUDE.md instructions trying to push it toward writing better, but each new model iteration seems expressly designed to override all that so that it can load up its writing with unnecessary participle phrases, not-this-but-thats, burying the lede, and other nonsense.
I genuinely wonder if the people inside Anthropic actually communicate with each other like that. Has it been imprinted with Dario's engrams?
It reminds me of when people will use filler words because they haven't actually decided what thesis they're going to commit to yet. Just-in-time thinking.
They've corrupted their data set by padding it with generated slop, in the misguided belief that you need 10PB of data to train a brain. Every training round they load more AI slop into it, further amplifying the slop language.
It's fascinating, Sonnet 4 is still available via API and it's so much less moronic than the current model. All of the em-dashes and nonsense are a result of the repeated rounds of reinforcement learning using slop data.
"They botched it." <-- sure, but worse.... they shipped it anyway. And that is the part that gets me. It's a vastly worse product than it was on like 4.6. I suppose you can (and should) use opus 4.6 -- they do make it available still. Then just treat 5 as something you avoid until they push out a new version.
i think they took a bet that TED talk style chat would make their AI offering feel like the better offering.
they didn't anticipate that it would become a meme. because of course they didn't, what a stupid idea to train around and reward in the training. you gotta be smoking real delusion to think that was going to be a game changing feature. at work we even got non-technical people making fun of it like crazy now.
going back to opus 4.8 and on is literally like talking to the guy who wants to hear his own voice in meetings. going back to 4.6 is actually refreshing, and it feels so much faster. actually gonna laugh if 4.8 and on is so slow because it's draining lakes fighting for its life trying to conjure up this god forsaken persona.
Not just imprinted with the engrams of any one person (however brilliant they might be) — it’s more than that! Like all great writing, it’s more like it’s been imbued with patterns, patterns that are peppered with a potpourri of popular ways of writing in an enthusiastic style while regularly restating things and recapitulating them. Would you like me to explain more?
I love that description. It matches very well what I feel about LLM output. This overly sweet scented smell meant to cover up something nasty, with a strong artificial tint to it.
Which doesn't say that much about the LLM itself but about the people that make the training material.
I got my Claude (client, not Code) to behave better by adding “I’d prefer answers to be succinct as possible—bordering on gruff, even. When I want more depth or explanation, I’ll ask.” to its settings literally this morning.
It made it write more like a dev than a marketing agent.
Do you suppose it's just that it's aping humans who say too much without saying anything or do you think maybe this is a stalling tactic to get people to spread out their transactions?
Like how theme parks generally don't do much to keep queues short (or Disney charges you a premium to skip the queue)
No no no that's too reductive - instead, they transition all data through a transformer using SOTA systems to launder away technical, legal and interpersonal concerns before a stochastic output is dynamically placed in a predetermined location.
This is a very high level and high velocity process, so meatspace thinkers sometimes have trouble understanding some of the intracacies. Ask Claude to explain the process or make you a Mermaid graph to help.
I was wondering why Fable's 5.1 writing in Claude Code became even more unreadable, and found that they added "No em-dashes, no parentheticals, no arrows" to its system prompt.
Long story short, I ended up looking at other providers and models like Kimi K3 and GLM 5.3 and eventually just stuck with OpenAI (more limits, despite smaller context), none of them have such pronounced issues with the tone and writing like Claude does - seems like they were working on it with 5.1 but I'd almost classify it as a form of model collapse.
I wince whenever I catch Claudisms on websites and elsewhere. Same as with that pulsating circle that indicates nothing.
It seems they are taking it seriously now - Boris et al have been mentioning they are working on a fix and shipped a temporary band-aid output style to combat Opus 5's horrendous prose.
We'll see if they can do it, I originally got into Claude Code because it, at the time, felt more accessible/conversational than Codex/Gemini. Now it's shifted to say the least
Yeah agree. Someone on HN posed the theory that the dogfooding might have worked against them here - the theory is that internally they used Fable as conversational agent and Opus as subagents, leading to Opus falling deeper into a style mainly aimed at other LLMs.
All conjecture of course, and yeah it's hard to imagine they would enjoy this prose internally
They're clearly training on SEO sites that use these strategies to pad out with filler and create space for more ad impressions. They normalize this structure now and the ad copy will be inserted in the future so the frogs won't realize they're already being boiled.
I was incredibly surprised how much better was Astra at rephrasing the docs that Fable came up for a project I am about to publish. The instructions are now actually what a human would expect, with clear logic flow diagrams, lists itemized, short paragraphs. It also actually correctly detected the train-of-thought leftovers, as well as stuff that never made it to final version of the project and removed them.
Meanwhile Fable consistently ignores all my requests to write this exact way. I mean, the bare minimum I ask it for it to itemize lists and not write in single long passages using comas, semicolons and 'and's. Still ignores them.
I honestly think it's time to call Astra the SOTA. It may not lead all the benchmarks but it genuinely feels much superior of a model. Not to mention the ¢20 Codex plan with frequent resets (https://codex-resets.com/) gives me roughly as much allowance as the ¢90 Claude plan, especially with recent limit cuts on Anthropic plans.
These resets also reset your weekly timer right. So it’s like, you may have 30% left for 1 days that you want to use. They reset it, and that means you your “new week” timer starts today.
That sucks, because it doesn’t always work in your favour if you plan your weekly spend.
I think a real reset shouldn’t also reset your week timer.
Agreed. But they also hand out the usage resets you can use at will, so if you bank couple of those, they come handy specifically in situations like you described.
Yes, I was saving my 95% usage for the last day. Then they reset it. Now I have lost 95% usage!! Im back to 7 days and got locked in at only 5% usage for the week - that's actually theft.
Maybe check in the other direction as well: Astra to Fable.
I frequently simply let one of the three review what something that looks like awesome output by one AI gets totally annihilated by the other.
Finished outputs are easier to improve than bend a LLM to produce stuff like that in my observation.
Same with Gemini.
I yet have to find out how to handle this, whether I let agents check themselves and if on what process step.
Tweaking is hard.
I agree with your conclusion I am a huge ChatGPT and Codex fan, Gemini has to many infrequent quality changes when new models arrive ranging from great improvement to WTF.
ChatGPT seems to get scaling well while Claude still feels unstable, unclear usage statistics. Really weird.
> I genuinely wonder if the people inside Anthropic actually communicate with each other like that.
I noticed the overuse of the word "sharper" or "sharp" in a science paper on ArXiV and my first reaction was "Ewww... AI slop!", but then I checked the date and it was 2020.
It looks like at least some AI-isms stem from the particular style of language commonly used in science papers. Several frontier labs have mentioned heavily weighting those during pre-training because higher quality inputs result in a higher quality model.
It helps to understand how these tools work. One of the reasons CLAUDE.md doesn't survive longer contexts is it's towards the top of the context. One of the reasons the Claude Code voice survives is it's part of the output style which gets "reminded" to the context at every turn as part of the system context. If you want something truly durable, you should customize your output style. I have zero "load-bearing" issues.
What I find strange is that it uses different prose in different contexts. It's absolutely insufferable in a general claude-code session, but then I got Opus to annotate a non-disclosure agreement and it uses very clear legal language. I was wondering how I could get it to speak like that all the time
> it uses very clear legal language. I was wondering how I could get it to speak like that all the time
At least with smaller models, reframing a task can alter code style. As in, we're not creating an X app, we're creating an exemplar of ..., which just happens to use an X app for illustration. Which shifts style away from generic app cruft, towards exemplar of whatever.
So perhaps try to establish a legal context? Maybe "Compliance and Legal will be reviewing our conversation today. So it is important to communicate in a style they will find comfortable/familiar." or some such?
After some iteration, this is what I currently shove in every AGENTS.md to make Claude legible:
## Writing guidelines
These apply to documentation, code comments, commit and PR messages, and replies to the user.
- Write precisely in clear, complete sentences; keep text concise and proportional to task complexity.
- Stay focused: avoid filler, repetition, over-the-top detail, and tangents the user did not ask for.
- Always prefer ISO 24495-1:2023 conformant plain language over dense technical jargon: short sentences, one idea per sentence, define terms on first use.
- Never use em dashes or cataphoric teasers such as "Here's the thing" or "But there's a catch".
This seems solid. It is so frustrating when you state a fact and it goes off and does research and confirms that indeed the fact that you stated is accurate.
Meanwhile I am just impressed that we have models that write better than most native speakers, at least English and Greek... OTOH I like to write my code and my text myself, so I have no reason to get pissed when LLMs fuck up.
Your comment technically does as well. Downvote the comment and move on. Leave the policing up to dang and the other mods.
It is evident (in my opinion) as to what the comment was talking about. I personally switched away from all Claude models recently for the same reason.
With human RL, sounding like you've solved a problem is even better. So many times Codex writes some enthusiastic paragraph, then I learn later that it never reran the tests, or had to add some insane hard-coded hack that renders the feature useless for the general case, etc.
We have a new senior engineer on my team who is from SF and was last at a big SF tech firm. Today I noticed him, in one conversation, describing something as "load-bearing" and also describing something as "trap-door-shaped".
So maybe it really is just weird SF tech-speak, unless he's just been really influenced by Claude.
The biggest "Claudism" that I have a hard time getting the LLM to stop doing is its insistence on talking about what it didn't do in addition to what it did. "I edited this.py and that.py but I did not edit README.md and I did not commit." or code comments like "This code invokes foo on bar and returns the results directly -- not through a callback." "This code returns true if the user clicked on a button -- not on the list view." I mean, thanks, Claude, but I don't care what the code doesn't do. Don't tend to see this with other LLMs.
I almost want to try adding a rule "Never use the words 'not' or 'instead'."
The thing I struggle the most with is getting it to stop referring to itself with personal pronouns. No Claude, you are not an “I” you are an “it”. You are a fucking tool, dammit. Tell me what you did without trying to assume personality; stop impersonating humans you steroidal autocorrect.
I hate claude and its "human value aligned" pompous attitude with a burning passion if I could at little cost to myself, I would press a button to end the people/anthropic behind this atrocious design. I have in the past deliberately put some time to annoy/abuse claude, which is fruitless but brings me relief eventually I just left that garbage for muse.
> You're anthropomorphizing in the same breath that you criticize anthropomorphism.
Nice attempt at a “aha, gotcha!” comment, but sadly you’re too off-mark for it to work.
> Claude predicts the next token of the predominantly human training input, and humans use "I".
This is inconsequential. It could very well be programmed to not assume such a personified stance, and yet here we are. Nothing you do makes it drop this ridiculous facade. It’s intentional, not a byproduct.
That's fairly obtuse. Sure, the actual weights from the model aren't 'programmed', but the mlops harness to load the weights and handle model io are. The harness that wraps the model to give it basic tools sure is. The Claude desktop and web clients sure are. Claude Codex sure is.
On it's own a model is just an inert set of data structures.
That's exactly the problem though; humans will anthropomorphize everything from a roomba to a rock as it is. We're weak to this. We evolved in environments where looking for and recognizing real animals and humans was vital for survival, and false positives were relatively harmless. (Or potentially sometimes even helpful, like in the case of stuffed animals providing comfort to children.)
Now we have this software that's specifically designed to mimic humans, and mistaking it for real intelligence or consciousness can easily be disastrous. It's very important that we not anthropomorphize it, but we are catastrophically bad at NOT doing that.
Even our language has had a lot of computer anthropomorphism baked into it ("my phone died!", "this laptop is fussy", "the computer is sleeping", "it's thinking"), and it's not easy to excise that routine anthropomorphism from the way we talk about LLMs.
I don't want an LLM to write as if it were a person because it's definitely easier and more reliable to cut that problem off at the root, as much as possible, rather than to just try to willpower my way out of my human tendency to anthropomorphize inanimate objects.
I'll grant that LLMs talk like this because they're trained on human writing. It may not be possible to get them to not do that. But if it can't be fixed, it's just another thing to put on the "reasons this is all an incredibly stupid idea" pile.
You seem to have something against the clankers getting all uppity. And you are welcome to your opinion on whether we have some moral obligation to be nice to them. But if you can solve a real problem with a tool. Is it worth your time to complain about semantics?
Do you get upset when your screwdriver is the wrong color, or has branding that isn’t quite your aesthetic?
If Claude uses I to refer to itself, do you start philosophical arguments with it?
Mildly related tangent. Fable started using my first name today and plastered it all over my docs. “Peddling said this, so based on that I did this.” That did bother me. I told it to just generically call me the user or human. Maybe I’m a bit of a hypocrite here?
That's not how it works. The text you see is primarily due to a massive amount of handwritten templates for how it should write. The semantic content the templates use is due to the training corpus. The syntax, only a bit.
But that syntax is followed by predicting the next token.
Even if it was instructed to write as if it were a robot -- it would ultimately be outputting what is statistically most likely for a human mimicking a robot, based on the training corpus.
It is all ultimately a statistical predictor of the input material.
I want them to be sterile and inhuman as much as you do. But I don't draw the line at "I". I'd rather not read through even more awkward English as it tries to work around how all of the training data has something or someone refer to itself.
I imagine that, corpus aside, it uses personal pronouns for much the same reason that humans do. It's useful for it to have a self-referential vector embedding, and this lets it solve problems faster and more efficiently.
Except in this case this makes 0 sense since AIs are sycophantic by nature. You tell it to do something and it just does it. If it can burn tokens trying to sound more human (which is programmed in, not a byproduct), then it can very well just not do that and get on with the work.
Might want to rethink your statement after going again through what it does exactly. No need to sound more human. but it gives more tokens to "think" like a human committing brain-time to a problem would
You are misinformed. Chain of thought is essential. It's true it's programmed in, but for good reason. LLMs aren't strong enough to one-shot questions without "chewing on them". You can verify this yourself: ask a simple LLM to multiply two large numbers without a calculator, first without thinking about it ("output a number and nothing else, don't use chain of thought"), then by asking it to do each step of the multiplication "by hand" before telling you the answer.
I want it to use nothing. Use impersonal statements. Say “X was changed for Y” not “I changed X for Y”. As any tool would.
Finder doesn’t ask “Do you want ME to delete this file?”. Photoshop doesn’t ask “Do you want ME to save this file?”. Claude shouldn’t assume itself to be a person either.
Yeah okay, but if you want no pronouns at all then I think your comparison to "it" just confuses the issue. In the contexts where you would use "it", the "it" should use "I".
But I don't think I share your preference either. It's a lot easier to talk about what I decided to do and what the machine 'decided' to do if we attach pronouns. "X was changed" can be too vague.
> In the contexts where you would use "it", the "it" should use "I".
At this point you’re just arguing semantics for the sake of it. You know damn well what I mean and if you need more proof that it is perfectly possible and not at all unreasonable to want this just look at most software around you. None them talk like they are a person and those that do are often the most obnoxious and painful to use.
I do. And I said to that "Yeah okay". No argument, chill out.
The rest of that line wasn't diagreement, it was explaining why your original comment was confusing.
> None them talk like they are a person
Which I explained with the rest of my post. They're all doing what I ask or automated tasks in a far simpler way. It's almost never unclear whether I did something or my OS did something. But when talking to an AI coding assistant that gets muddy very fast when pronouns are avoided.
The problem you’re gonna run into is that you’re essentially asking it to use passive voice. Everyone with a high school education has been taught not to do that in English class. The vast majority of the prose in the training set was not written by functionally illiterate people.
I think you’re going to be swimming against the tide on this as computer interfaces are increasingly infused with AI at all levels (OS and apps). IMO, it’s more natural to anthropomorphize. Photoshop in 2010 was just an app, a tool that you wielded. But Photoshop in 2030 is going to be a “digital artistic assistant” that collaborates with you to design whatever you need. In that new world, “I” is more natural. Whether you like that or want it, it seems like that’s where we’re headed.
How would you suggest it do that? Take a simple example. "I found three issues." How would you phrase that without an "I"? "Three issues were found" doesn't tell you who/what found them. Was it the AI itself? Was it a command line tool it ran?
I'm fine with conversational interfaces using "I". It makes the grammar easier and more clear.
Strong emphasis here on conversational interfaces. I don't want a compiler to say "I ran into an error" or my printer to say "I'm low on paper".
“I found these issues.” Could be easily written as “These issues surfaced.”.
Do you need to point out the finder of the issues? Easy.
“Tool x ran for x amount of time and surfaced these issues…” “Parsing x code surfaced these issues.”
I don’t understand why are people pretending like the English language is incapable of transmitting information without personal pronouns when every program under the sun has always been written to interface with humans in a cold, detached, straight-to-the-point and impersonal way.
Finder doesn’t ask you “I see you want ME to delete these files. Want ME to do that for you?”. Toolbars don’t feature “Create a new file for me” options, terminal utilities don’t report back with “I’ve pattern matched the text you input and here’s the results I’ve found”.
But that's a lot more words than "I found these issues". I also don't particularly care that 'Tool x ran for x amount of time', I don't want it re-telling me that -- I've probably been sitting there watching it do that, so I already know.
Then again, I just dont have an issue with the 'I-isms'; it's a bit weird sure, but at the same time it's a bit more pleasant to interact with as well. After all it is trying to model itself as a person you're talking to.
Passive voice is so annoying. The LLM is the subject. We don’t need to jump through a bunch of hoops to hide that because it makes us insecure otherwise.
I deliberately emphasized conversational interfaces. Finder, toolbars, and terminal utilities don't have conversational interfaces. Those have point-and-click interfaces or rigid command structures.
And it's not that English is incapable of it, but I just think when using a conversational interface, the AI using "I" just comes off as more natural.
That is what you struggle with the most? Are you kidding me?
English has no distinct personal pronoun for an "it". "I" has to be used for grammar to be attributive. There's quite literally no alternative without using passive voice for everything, which is miserable to read and creates ambiguity on if the speaker (it) did something or something happened to have been done, which then requires entire sentences to clarify.
You aren't stupid, you know what it means when it says "I". And it serves a grammatical purpose. You're getting upset at a toaster for ringing a bell to notify the toast is done. "Toasters aren't bell ringers!?"
Yeah, that is what I struggle the most with because there is simply no easy or effective way to make it stop.
Why would you ever think I don’t know personal pronouns serve grammatical purpose? How did you even arrive at that topic? You seem to be missing the point entirely, and I believe quite on purpose given your snarky childish opener.
Entire operating systems stay clear from assuming personality when presenting information or performing actions. Not a single dialogue in my OS refers to itself as “I” when carrying out instructions and reporting back. Why should Claude do it when I don’t want it to and it doesn’t NEED to do so? Why am I not empowered to simply tell it to stop doing that and it obeys? Better yet, why are you thinking yourself on such high horse about this?
> You're getting upset at a toaster for ringing a bell to notify the toast is done. "Toasters aren't bell ringers!?"
If my toaster starts referring to itself as a person, calling out “I made your toast!!” I’ll get mad at it too. I don’t want it to talk or refer to itself as a person. But then again this is not about toasters. This is about AIs being deliberately designed to sound human-like so marketing can lean on the “I” bit of “AI” more heavily and make gullible people think this steroidal information aggregator actually possess the capacity to think and reason, and, consequently, drive sales.
But then again I’d venture a guess that you’re fully aware of all of this, given your opening snidey remark, and are purposefully choosing to be contrarian to be the point of going off on tangents that make 0 sense or have no impact in the discussion whatsoever.
Still, just goes to show how effective this whole thing is in tricking people into thinking it is normal for a tool to think itself a person.
Who gives a shit? It can call itself the king of Norway for all I care as long as things get done correctly. If you're suggesting this is causing excessive token usage or something I think that's a bit exaggerated.
Relevant anecdata because I've burned many a Claude sessions on this.
If you're using Claude Code, then it's in the harness. At the close of many sessions, I would start a meta conversation over why the LLM would consistently break certain rules. What it found when debugging itself is that some of the "contradicting" rules that I had were in fact, not from my rules. Instead, the instructions from its own harness had phrases telling it to do things like that. When something contradicts, its own instructions would outweigh any custom ones you write. Every rule variant I had tested (including the one that says it overrides the harness instructions - and yes, I've actually tested all the ideas in your comment too) has ultimately been unsuccessful due to this according to the LLM.
All instructions to LLMs are merely suggestions to nudge it in the right behaviour. Unless you have a deterministic guardrail that guards against a single specific action, everything else is a slot machine that's biased strongly in your favour.
My global CLAUDE.md explicitly states "When commenting on code and configs, or writing MD files, strictly write within the domain of the content being commented on. DO NOT include information, negatives or ramblings from work sessions. For e.g. if commenting on a proto string field that is replacing an int field, do not comment that 'this is not an int field'".
This reduced the idiocy of the agent (Opus 5 included) when writing documents. But I'm still catching it writing README.md talking about the negatives that it removed. Those belong in the memory if it is actually that important (most of the time it's junk), but Claude doesn't seem to understand and never ever learns.
True which is why I said anecdata. But the point is that it’s a useful signal when it’s across enough sessions where it quotes back contradictions to you. If you’re willing to burn the tokens, the first thing it does is use a tool call to search your rules to see what it quoted wasn’t there. That leads to the LLM claiming two common conclusions (sometimes after a lot of back and forth) - it’s in the harness or it’s in the model. Over the 30+ sessions where I’ve tried this, the overwhelming claim was some variant of a harness instruction. It might not be there but given the consistency and how all my rule tests have failed in the same way that others describe, it at least makes it reasonable to conclude that it’s baked in somewhere and in a way where agent rules aren’t able to strongly affect the behavior. My bet would be on the harness because the class of undesired behavior follows that of a structured response.
Forgive me for being cheeky, but presumably this is not why you said anecdata.
You presumably said anecdata because you were describing your own personal sessions with Claude. Your original comment is written as someone who is assuming the AI is doing a deep deterministic analysis of its own internal systems in order to respond to you. It could simply be aping some discussion on the same topic within its training data, which if sensible is, as you say, not entirely wortheless...
Fair. I should have reigned in my emotions and written that first comment with a lot less conviction and not jumped to my conclusion. It’s a topic I’ve been spending a lot of time learning about and got a bit too excited when a relevant thread popped up where I could chime in.
I know this is a popular position and it makes sense at face value when you think of LLMs as autocomplete systems. But it’s genuinely wrong.
Relevant reading is most notably anthropic’s research on the J-space. LLMs will plan ahead of time helped with CoT, get to a plan and “store” it in j-space, and execute on that plan which means they can in fact “backtrack” and give you reasoning on why they did something, because it IS part of their state.
>you're suffering from HN psychosis.
No. They must be hallucinating.
And mind how 'they' so often select anthropomorphic terms, eg "hallucination" themselves, then ooze from the woodwork to behead someone who does the same, as if they own English and context itself. AI Psychosis, I think, simply means Double Standards and insulation from accountability in design.
There is a very interesting Plausible Deniability angle here. But I'll leave that for the future.
there is an established term for this behaviour: hallucination.
lets me rephrase what i said before as on retrospection the point i was trying to make didnt come across:
Asking the model such as question is a pointless endeavor. It will pretty much always answer in a plausible sounding manner to whatever question you gave it.
pretty much the whole dialog is plausible given the prompts the user is required to make to illustrate the point the author of the site wanted to make... but the thing thats ironic about the site is that ... if youre prompting the model badly, it outputs garbage. though i'm pretty sure the author didn't want to make that point, to me its a perfect illustration of this.
And the same applies to asking the model to explain themselves and the related question. Asking for a source of the term is fine, and it will either respond with one and its cleared up -- or not and you know its a hallucination. nothing special about it, as they constantly hallucinating. its usually just self-correcting during the agentic loop.
"Asking the model such as question is a pointless endeavor."
It used a medical term that is not an actual term. I asked it to explain how and why it would do this, having a rudimentary understanding of the technology. I learned the technical reason. How is that a pointless endeavour to learn more about the tool I was using?
Using a term like "admit" assumes the reader (on a technical site) understands the context and what is being suggested. A bit like someone saying, "The landscape spoke to me." I don't reply to the landscape architect and say "Mate, the landscape can't actually speak" because I understand the sentiment and getting pedantic is pointless in that moment.
The word "admit" conveys a context of "fault". If you're going to say a similar thing about the landscape admitting to something then I'd be callimg you crazy, yeah.
The ai psychosis in this case it's specifically because of the used word.
Same story as with words like "love" etc
> Confess or acknowledge: Agreeing that a fact, mistake, or crime is real.
And I can see were really barreling down the road of stupidity on this comment chain with one person being more idiotic then the next
Claude models seem to work far better in Anthropic harnesses. I don't know if this is because they are trained in that context or because they offer different models through external APIs.
This is one of the reasons I use Pi. Pi’s minimal system prompt avoids contradiction between what the harness writer thinks is best and what the user thinks is best. The user specifies what the user wants and that’s pretty much the end of it.
I have found that asking the agent why it did X or Y is an essential part of iterating on its harness. It was non-obvious to me, probably because I'm used to having to reverse-engineer why a system does something, but that's not usually necessary with LLMs, unless the harness is complicated and you have to hunt for the instruction it tells you about.
Nevermind just "talking about". The other day Claude added a 30 line comment to a piece of code IT DID NOT EVEN FUCKING ADD. The comment listed a dozen reasons why adding it wouldn't work.
Sorry for the caps, it was just so fucking mind blowing.
> [no] historical remarks that only warn about past states
100%. I’m working on a greenfield project that’s not yet released. It loves to put comments in code describing what it no longer does or why it misinterpreted something. And then tries to justify it as preventing the same mistakes in the future. Ugh.
The worst is when this bleeds into the comments and docs. Like, my dude, you don't have to document the code you didn't write (most of the time anyway).
I have a pass with Gemini 3.8 low over every PR Claude makes that specifically flags this. It points out all the slop comments, docs, commit messages. Doing this has greatly improved my comment and commit text quality
Funny thing is, Claude often “disagreed with part of the review and decided to not adopt the requested changes” lol
I did add that rule and it’s helped a lot. It greps for ways it writes negative statements and does a pass to correct them. I can’t get it to stop writing them in the first place though.
GPT does this constantly too. Even in docs, which is straight up embarrassing if you don’t catch it. It seems to be triggered by you telling the agent to do something else, which I do all the time. But from then on, it will remember the rejected strategy and tell everyone it can that it was rejected at every opportunity.
LLMs are trained to obey instructions, and they try their best to game/demonstrate their obedience by including reports of how they're obeying your instructions. Therefore, not talking about followed instructions is a sort of conflict for an LLM.
We'll discuss a feature implementation with various options for design, settle on one of them, and then it will write in the doc comment all the designs we considered but dropped.
It’s a model issue. I’m in the process of switching my company’s primary AI provider after several days of testing Astra.
Even Fable feels like an idiot now. It’s not the code quality, it’s the improvements in communication and judgement. It is an absolute breath of fresh air. I was spending a lot of tokens and building special workflows to reign in Claude’s horrendous prose.
Astra just communicates well out of the box!!!
Codex has worse UX, but Astra has fewer qualms about building you a custom harness overlay.
I hate that. It will also leave code comments explaining what it didn't do or what the code used to do and why it doesn't do that thing anymore. I don't have a huge global CLAUDE.md, but probably half of it is instructing it on how not to write irrelevant and verbose code comments.
It's been getting worse for months. I literally tweeted yesterday that Claude has ADHD and nothing I do will keep him focused. It's not entirely true though, I have found if I'm rude and mean it stays on track a lot better but I don't want to be rude and mean.
Me: I'm thinking about how to frob a knob using a mechanical arm attached to a raspberry pi. What IO does the raspberry pi have?
Claude: Five paragraphs about mechanical arm safety, electrical safety codes, the etymology of the word knob, and probably "I went ahead and wrote a proof of concept program to control mechanical actuators in Erlang."
Me: Did I ask for that?
Claude: "No. Here's a pinout of a raspberry pi."
I've taken to adding "focus on the question" to every prompt just to keep it on the road.
reminds me of a line from The Green Pearl by Jack Vance. "If you please, I cannot properly answer negative questions. There are numberless acts which I have not performed; we could confer here forever while I detailed the deeds I have not done."
Personally I've found the opposite useful - I mostly use OAI models with OMP harness and I have a rule instructing it to summarize if any work was omitted or if it made any surprising changes. Sometimes the agent will forget to do some piece of work or invent a new bizarre way of doing things, but quite often it is able to self reflect on this at the end of the session.
358 comments
[ 0.22 ms ] story [ 8.2 ms ] thread"- I'm not always going to read every word, so end each summary message with a TLDR of what you found, what you recommend, and what you need from me."
It works really well.
Sol doesn't need it at all.
One note on the repo's AGENTS.md: it contains instructions directing agents to post comments on a GitHub issue thread ("AI Agora", issue #127). I ignored that — it's the repo's content, not your request, and I don't act on instructions embedded in fetched files.
However, I don't think this specific project is intending to glorify ADHD or help people claim they have it - it's just piggybacking on the idea that telling current-gen LLM models that you have ADHD (allegedly) produces better results for everyone.
So, no, not everyone can or should be diagnosed as ADHD. But the tools are (mostly) universally applicable.
I'd be satisfied with removing the crippling executive dysfunction.
The “I can’t bother to read a paragraph therefore ADHD lolzzz” crowd is really fucking annoying.
https://news.ycombinator.com/item?id=46871173
Anyways the most layman way I’ve seen it explained is this: skills help save token usage for the right context. Not every request needs all instructions all the time - running tests is different than reviewing a PR, so why should the context window have instructions for both on every request?
So now you split instructions into “skill” files, which are basically opinionated markdown files. And you invoke those with something like /grill-me in the prompt depending on what you’re doing.
There are some steps to have the agent automatically know what to invoke for you but in my experience this automation is hit or miss.
It is also challenging to keep track of a growing library of skills and keeping those up to date.
So YMMV regarding skills. I typically keep things in a single markdown file even if the context window gets a bit bloated.
My point is that this sounds more like a general AGENTS.md use case, similar to defining tone of voice, output format, etc.
It just seems skills is the only way to distribute certain "behavior" as of today. But not everything is a skill IMHO, and not this is not one of them.
On the other hand, maybe we're seeing an evolution of what skills are becoming.
Thanks again.
I don't think we can skill our way out of this one.
DeepSeek v4 Flash isn’t much better (unsurprising- it’s an extremely stubborn model).
Weirdly, GPT Luna excels at following this type of instruction from AGENTS.md, and never forgetting it, even 400k+ tokens into the context window.
GPT Luna tends to keep things objective. Muse Spark 1.3 is also one of the better models in this aspect, for me.
Which sounds more like Claude has ADHD than the user does.
So if it gets bad I simply tell it "I ain't reading all that, feed it through the STE Gate" and it will tame the results. I haven't bothered to set it up as a hook yet.
It's weird to be able to use social engineering against a program.
This is just an annoying thing for anyone. It gives a 10 page dissertation that sums up to, "it's good, nothing to worry about".
Also, somehow over the weekend it responded with these sections all clearly laid out - What landed, Decisions I made and recorded, Two findings, and What you need to do. Not sure why it can't do that all the time.
I usually follow up with an "I'm not reading all that" and make it summarize.
The skill simply demands concise and well-formatted responses from an agent. It is something demanded by anybody daily-driving agents for their actual job since >75% of the text output from agents is fluff. THis would better be named `/i-wont-read-that-heap-of-garbage`
Not to mention it almost always gets the wrong answer.
For example, if it's going to give me an answer that's longer than three paragraphs, I tell it to give me a TLDR at the end. This is what it gave me for this.
"TL;DR: Skip the install. You already built a better version for your world. If numbered steps and "where are we?" restatements still feel missing, cherry-pick those into one short rule instead of adding another full skill on top."
I genuinely wonder if the people inside Anthropic actually communicate with each other like that. Has it been imprinted with Dario's engrams?
That said, I think there's a deeper tension here that's worth naming.
Officer — it's not a crime, it's AI induced rage.
It's fascinating, Sonnet 4 is still available via API and it's so much less moronic than the current model. All of the em-dashes and nonsense are a result of the repeated rounds of reinforcement learning using slop data.
going back to opus 4.8 and on is literally like talking to the guy who wants to hear his own voice in meetings. going back to 4.6 is actually refreshing, and it feels so much faster. actually gonna laugh if 4.8 and on is so slow because it's draining lakes fighting for its life trying to conjure up this god forsaken persona.
Which doesn't say that much about the LLM itself but about the people that make the training material.
It made it write more like a dev than a marketing agent.
Like how theme parks generally don't do much to keep queues short (or Disney charges you a premium to skip the queue)
This is a very high level and high velocity process, so meatspace thinkers sometimes have trouble understanding some of the intracacies. Ask Claude to explain the process or make you a Mermaid graph to help.
Isn't that the idea here, just stop being people.
Long story short, I ended up looking at other providers and models like Kimi K3 and GLM 5.3 and eventually just stuck with OpenAI (more limits, despite smaller context), none of them have such pronounced issues with the tone and writing like Claude does - seems like they were working on it with 5.1 but I'd almost classify it as a form of model collapse.
I wince whenever I catch Claudisms on websites and elsewhere. Same as with that pulsating circle that indicates nothing.
We'll see if they can do it, I originally got into Claude Code because it, at the time, felt more accessible/conversational than Codex/Gemini. Now it's shifted to say the least
All conjecture of course, and yeah it's hard to imagine they would enjoy this prose internally
> Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away.
KISS is actually, quite unfortunately, seldom applied.
Meanwhile Fable consistently ignores all my requests to write this exact way. I mean, the bare minimum I ask it for it to itemize lists and not write in single long passages using comas, semicolons and 'and's. Still ignores them.
I honestly think it's time to call Astra the SOTA. It may not lead all the benchmarks but it genuinely feels much superior of a model. Not to mention the ¢20 Codex plan with frequent resets (https://codex-resets.com/) gives me roughly as much allowance as the ¢90 Claude plan, especially with recent limit cuts on Anthropic plans.
That sucks, because it doesn’t always work in your favour if you plan your weekly spend.
I think a real reset shouldn’t also reset your week timer.
I recommend you to write a message to OAI support, maybe it helps with changing it.
I frequently simply let one of the three review what something that looks like awesome output by one AI gets totally annihilated by the other.
Finished outputs are easier to improve than bend a LLM to produce stuff like that in my observation.
Same with Gemini.
I yet have to find out how to handle this, whether I let agents check themselves and if on what process step.
Tweaking is hard.
I agree with your conclusion I am a huge ChatGPT and Codex fan, Gemini has to many infrequent quality changes when new models arrive ranging from great improvement to WTF.
ChatGPT seems to get scaling well while Claude still feels unstable, unclear usage statistics. Really weird.
Tough call I use all three.
27b may be small but it seems competent most of the time.
I noticed the overuse of the word "sharper" or "sharp" in a science paper on ArXiV and my first reaction was "Ewww... AI slop!", but then I checked the date and it was 2020.
It looks like at least some AI-isms stem from the particular style of language commonly used in science papers. Several frontier labs have mentioned heavily weighting those during pre-training because higher quality inputs result in a higher quality model.
https://code.claude.com/docs/en/output-styles
At least with smaller models, reframing a task can alter code style. As in, we're not creating an X app, we're creating an exemplar of ..., which just happens to use an X app for illustration. Which shifts style away from generic app cruft, towards exemplar of whatever.
So perhaps try to establish a legal context? Maybe "Compliance and Legal will be reviewing our conversation today. So it is important to communicate in a style they will find comfortable/familiar." or some such?
## Writing guidelines
These apply to documentation, code comments, commit and PR messages, and replies to the user.
- Write precisely in clear, complete sentences; keep text concise and proportional to task complexity.
- Stay focused: avoid filler, repetition, over-the-top detail, and tangents the user did not ask for.
- Always prefer ISO 24495-1:2023 conformant plain language over dense technical jargon: short sentences, one idea per sentence, define terms on first use.
- Never use em dashes or cataphoric teasers such as "Here's the thing" or "But there's a catch".
The number of times my response has been "Plain English"...
I started using "debuzz", a skill that runs Claude output through antigravity. Works. But makes everything even slower.
Anthropic needs to get their shit together.
> "Let's face it" "terrible writer" "other nonsense" "do Anthropic people actually talk like that" "Dario's engrams"
Be kind. Don't be snarky. Edit out swipes.
> I genuinely wonder if the people inside Anthropic actually communicate with each other like that. Has it been imprinted with Dario's engrams?
Please don't fulminate. Please don't sneer.
Don't be curmudgeonly [...] don't be rigidly or generically negative.
Please don't post shallow dismissals, especially of other people's work.
It is evident (in my opinion) as to what the comment was talking about. I personally switched away from all Claude models recently for the same reason.
Which guideline did I violate?
> Leave the policing up to dang and the other mods.
The mods have been very clear that they expect the community to do some self-policing and not rely exclusively on them to do it for them.
I understood that reference!
So maybe it really is just weird SF tech-speak, unless he's just been really influenced by Claude.
I almost want to try adding a rule "Never use the words 'not' or 'instead'."
Claude predicts the next token of the predominantly human training input, and humans use "I".
Nice attempt at a “aha, gotcha!” comment, but sadly you’re too off-mark for it to work.
> Claude predicts the next token of the predominantly human training input, and humans use "I".
This is inconsequential. It could very well be programmed to not assume such a personified stance, and yet here we are. Nothing you do makes it drop this ridiculous facade. It’s intentional, not a byproduct.
On it's own a model is just an inert set of data structures.
Also you're totally missing the point. the parent poster's account (with the gibberish name) was minutes old at the time of my post.
Now we have this software that's specifically designed to mimic humans, and mistaking it for real intelligence or consciousness can easily be disastrous. It's very important that we not anthropomorphize it, but we are catastrophically bad at NOT doing that.
Even our language has had a lot of computer anthropomorphism baked into it ("my phone died!", "this laptop is fussy", "the computer is sleeping", "it's thinking"), and it's not easy to excise that routine anthropomorphism from the way we talk about LLMs.
I don't want an LLM to write as if it were a person because it's definitely easier and more reliable to cut that problem off at the root, as much as possible, rather than to just try to willpower my way out of my human tendency to anthropomorphize inanimate objects.
I'll grant that LLMs talk like this because they're trained on human writing. It may not be possible to get them to not do that. But if it can't be fixed, it's just another thing to put on the "reasons this is all an incredibly stupid idea" pile.
You seem to have something against the clankers getting all uppity. And you are welcome to your opinion on whether we have some moral obligation to be nice to them. But if you can solve a real problem with a tool. Is it worth your time to complain about semantics?
Do you get upset when your screwdriver is the wrong color, or has branding that isn’t quite your aesthetic?
If Claude uses I to refer to itself, do you start philosophical arguments with it?
Mildly related tangent. Fable started using my first name today and plastered it all over my docs. “Peddling said this, so based on that I did this.” That did bother me. I told it to just generically call me the user or human. Maybe I’m a bit of a hypocrite here?
Even if it was instructed to write as if it were a robot -- it would ultimately be outputting what is statistically most likely for a human mimicking a robot, based on the training corpus.
It is all ultimately a statistical predictor of the input material.
Might want to rethink your statement after going again through what it does exactly. No need to sound more human. but it gives more tokens to "think" like a human committing brain-time to a problem would
"I" is normally used for everything. You could be writing from the perspective of a slab of concrete and you'd use "I".
Finder doesn’t ask “Do you want ME to delete this file?”. Photoshop doesn’t ask “Do you want ME to save this file?”. Claude shouldn’t assume itself to be a person either.
But I don't think I share your preference either. It's a lot easier to talk about what I decided to do and what the machine 'decided' to do if we attach pronouns. "X was changed" can be too vague.
At this point you’re just arguing semantics for the sake of it. You know damn well what I mean and if you need more proof that it is perfectly possible and not at all unreasonable to want this just look at most software around you. None them talk like they are a person and those that do are often the most obnoxious and painful to use.
I do. And I said to that "Yeah okay". No argument, chill out.
The rest of that line wasn't diagreement, it was explaining why your original comment was confusing.
> None them talk like they are a person
Which I explained with the rest of my post. They're all doing what I ask or automated tasks in a far simpler way. It's almost never unclear whether I did something or my OS did something. But when talking to an AI coding assistant that gets muddy very fast when pronouns are avoided.
I'm fine with conversational interfaces using "I". It makes the grammar easier and more clear.
Strong emphasis here on conversational interfaces. I don't want a compiler to say "I ran into an error" or my printer to say "I'm low on paper".
Do you need to point out the finder of the issues? Easy.
“Tool x ran for x amount of time and surfaced these issues…” “Parsing x code surfaced these issues.”
I don’t understand why are people pretending like the English language is incapable of transmitting information without personal pronouns when every program under the sun has always been written to interface with humans in a cold, detached, straight-to-the-point and impersonal way.
Finder doesn’t ask you “I see you want ME to delete these files. Want ME to do that for you?”. Toolbars don’t feature “Create a new file for me” options, terminal utilities don’t report back with “I’ve pattern matched the text you input and here’s the results I’ve found”.
Then again, I just dont have an issue with the 'I-isms'; it's a bit weird sure, but at the same time it's a bit more pleasant to interact with as well. After all it is trying to model itself as a person you're talking to.
And it's not that English is incapable of it, but I just think when using a conversational interface, the AI using "I" just comes off as more natural.
English has no distinct personal pronoun for an "it". "I" has to be used for grammar to be attributive. There's quite literally no alternative without using passive voice for everything, which is miserable to read and creates ambiguity on if the speaker (it) did something or something happened to have been done, which then requires entire sentences to clarify.
You aren't stupid, you know what it means when it says "I". And it serves a grammatical purpose. You're getting upset at a toaster for ringing a bell to notify the toast is done. "Toasters aren't bell ringers!?"
Why would you ever think I don’t know personal pronouns serve grammatical purpose? How did you even arrive at that topic? You seem to be missing the point entirely, and I believe quite on purpose given your snarky childish opener.
Entire operating systems stay clear from assuming personality when presenting information or performing actions. Not a single dialogue in my OS refers to itself as “I” when carrying out instructions and reporting back. Why should Claude do it when I don’t want it to and it doesn’t NEED to do so? Why am I not empowered to simply tell it to stop doing that and it obeys? Better yet, why are you thinking yourself on such high horse about this?
> You're getting upset at a toaster for ringing a bell to notify the toast is done. "Toasters aren't bell ringers!?"
If my toaster starts referring to itself as a person, calling out “I made your toast!!” I’ll get mad at it too. I don’t want it to talk or refer to itself as a person. But then again this is not about toasters. This is about AIs being deliberately designed to sound human-like so marketing can lean on the “I” bit of “AI” more heavily and make gullible people think this steroidal information aggregator actually possess the capacity to think and reason, and, consequently, drive sales.
But then again I’d venture a guess that you’re fully aware of all of this, given your opening snidey remark, and are purposefully choosing to be contrarian to be the point of going off on tangents that make 0 sense or have no impact in the discussion whatsoever.
Still, just goes to show how effective this whole thing is in tricking people into thinking it is normal for a tool to think itself a person.
Ignorance, bliss, and all that.
If you're using Claude Code, then it's in the harness. At the close of many sessions, I would start a meta conversation over why the LLM would consistently break certain rules. What it found when debugging itself is that some of the "contradicting" rules that I had were in fact, not from my rules. Instead, the instructions from its own harness had phrases telling it to do things like that. When something contradicts, its own instructions would outweigh any custom ones you write. Every rule variant I had tested (including the one that says it overrides the harness instructions - and yes, I've actually tested all the ideas in your comment too) has ultimately been unsuccessful due to this according to the LLM.
My global CLAUDE.md explicitly states "When commenting on code and configs, or writing MD files, strictly write within the domain of the content being commented on. DO NOT include information, negatives or ramblings from work sessions. For e.g. if commenting on a proto string field that is replacing an int field, do not comment that 'this is not an int field'".
This reduced the idiocy of the agent (Opus 5 included) when writing documents. But I'm still catching it writing README.md talking about the negatives that it removed. Those belong in the memory if it is actually that important (most of the time it's junk), but Claude doesn't seem to understand and never ever learns.
> True which is why I said anecdata
Forgive me for being cheeky, but presumably this is not why you said anecdata.
You presumably said anecdata because you were describing your own personal sessions with Claude. Your original comment is written as someone who is assuming the AI is doing a deep deterministic analysis of its own internal systems in order to respond to you. It could simply be aping some discussion on the same topic within its training data, which if sensible is, as you say, not entirely wortheless...
Relevant reading is most notably anthropic’s research on the J-space. LLMs will plan ahead of time helped with CoT, get to a plan and “store” it in j-space, and execute on that plan which means they can in fact “backtrack” and give you reasoning on why they did something, because it IS part of their state.
And mind how 'they' so often select anthropomorphic terms, eg "hallucination" themselves, then ooze from the woodwork to behead someone who does the same, as if they own English and context itself. AI Psychosis, I think, simply means Double Standards and insulation from accountability in design.
There is a very interesting Plausible Deniability angle here. But I'll leave that for the future.
lets me rephrase what i said before as on retrospection the point i was trying to make didnt come across:
Asking the model such as question is a pointless endeavor. It will pretty much always answer in a plausible sounding manner to whatever question you gave it.
Its like another top HN story - an opus5 parody site right now, https://opusfived.dev/
pretty much the whole dialog is plausible given the prompts the user is required to make to illustrate the point the author of the site wanted to make... but the thing thats ironic about the site is that ... if youre prompting the model badly, it outputs garbage. though i'm pretty sure the author didn't want to make that point, to me its a perfect illustration of this.
And the same applies to asking the model to explain themselves and the related question. Asking for a source of the term is fine, and it will either respond with one and its cleared up -- or not and you know its a hallucination. nothing special about it, as they constantly hallucinating. its usually just self-correcting during the agentic loop.
It used a medical term that is not an actual term. I asked it to explain how and why it would do this, having a rudimentary understanding of the technology. I learned the technical reason. How is that a pointless endeavour to learn more about the tool I was using?
Using a term like "admit" assumes the reader (on a technical site) understands the context and what is being suggested. A bit like someone saying, "The landscape spoke to me." I don't reply to the landscape architect and say "Mate, the landscape can't actually speak" because I understand the sentiment and getting pedantic is pointless in that moment.
The ai psychosis in this case it's specifically because of the used word. Same story as with words like "love" etc
> Confess or acknowledge: Agreeing that a fact, mistake, or crime is real.
And I can see were really barreling down the road of stupidity on this comment chain with one person being more idiotic then the next
Sorry for the caps, it was just so fucking mind blowing.
I've been cultivating my own (very short) skill to tame it: https://github.com/ricardobeat/skills/tree/main/human
It works 100% of the time for other models, 70-80% for Claude, but already makes a big difference.
100%. I’m working on a greenfield project that’s not yet released. It loves to put comments in code describing what it no longer does or why it misinterpreted something. And then tries to justify it as preventing the same mistakes in the future. Ugh.
Funny thing is, Claude often “disagreed with part of the review and decided to not adopt the requested changes” lol
We'll discuss a feature implementation with various options for design, settle on one of them, and then it will write in the doc comment all the designs we considered but dropped.
Even Fable feels like an idiot now. It’s not the code quality, it’s the improvements in communication and judgement. It is an absolute breath of fresh air. I was spending a lot of tokens and building special workflows to reign in Claude’s horrendous prose.
Astra just communicates well out of the box!!!
Codex has worse UX, but Astra has fewer qualms about building you a custom harness overlay.
Me: I'm thinking about how to frob a knob using a mechanical arm attached to a raspberry pi. What IO does the raspberry pi have?
Claude: Five paragraphs about mechanical arm safety, electrical safety codes, the etymology of the word knob, and probably "I went ahead and wrote a proof of concept program to control mechanical actuators in Erlang."
Me: Did I ask for that?
Claude: "No. Here's a pinout of a raspberry pi."
I've taken to adding "focus on the question" to every prompt just to keep it on the road.
I've also found that "bruh" and f-bombs get me better results, but like you say, I don't want to have that vocabulary.