1. Constitution can't work without punitive enforcement, how will you punish agent/LLM? 2. Even if we can enforce laws for agents/LLM, just look at existing law system it is tug of war because we almost can't write…
Well, even without that AI can do human engineering and fishing or outright blackmail to get what they want from labs and government officials.
I have started with generating very detailed "feature" spec and going over it many times until it looked good to me. Then I made it write an "architecture doc" and plan how to implement all which was about 15 parts.…
I've been making a macos app with opus 4.8-5 and at first it was great, everything materialized in a week, but when I started tuning stuff and fixing performance problems I have spent a very frustrating month…
I had a genius response from Claude recently after asking how can it be marketed as smart and "almost AGI" despite being so stupid: "I compress the labour. Not the responsibility."
That can be true. On multiple occasions when claude did some BS I have asked it why and it explained that it is optimizing for task completion and not for communication.
I have a rule in claude.md: ``` ## Writing rules *Describe the code as it is now — no residue, no change-narration.* Artifacts (docs, plans, comments, commit messages) should describe the current code statically, as if…
It is sufficient not at all
Yeah, I should probably /clear more often. Compaction seem cheap by itself (all cached input and small output), but it often marks unnecessary files for pre-load.
Many very well made software written without any AI was never "shipped" because there were no people who wanted to pay for it, many very poorly made software was shipped because demand and marketing did the job. So…
I've actually found that compacting as often as possible, after planning, then between each implementation step works the best, it both unloads unnecessary context of previous edits and test runs, makes thinking…
My experience as well, I've been developing a native macos app using CC. As a web dev I didn't know much about the stack. Nothing too fancy a kind of folder gallery-player with tags embedded in filenames, a bit like…
I think it case of coding it may not be as bad, because new training data (AI generated code) is always empirically validated by tooling and by consumer. It may not be good but it mostly works, otherwise it is discarded…
So true. I am cloding a macos app (a domain I know little about), with Opus 4.8 xhigh, and it was glorious at first seeing the app materializing and working (notwithstanding tedious detailed feature spec write up), but…
I've made it write a /status-line thing to display context tokens in the status line and also a hook to stop and ask to continue or compact whenever it reaches 250k tokens. For subscription I have also made it stop at…
Many game ads on ios are already playable, I guess we're just one step away from what you describe.
> it has advanced significantly since early releases I have used Claude Code past few weeks and honestly can't tell if it is any better, or does anything different than Copilot in agent mode with same models.
I'd say it is quite opposite, a deep understanding of what you like and consequently understanding what will make a creation into exactly what you like. (Well I guess some people can create without understanding, just…
For me, even if I drop into "mental space" completely and stop seeing(or being aware of) real world while thinking about something I saw/did recently, vividness of this mental image will depend on how close I am to…
Good erotic literature does not only describe images, but also desires, emotions and sensations, all of which I think have different channels of imagination/recall.
For me visualization by itself is mostly useless, it is more of a concept of something arousing happening and vague visual flashes of something similar I have seen. It somewhat works, but nowhere near as effective as…
I feel like "intuition" really fits to what LLM does. From the input LLM intuitively produces some tokens/text. And "thinking" LLM essentially again just uses intuition on previously generated tokens which produces…
A bit sad that the language and framework so enjoyable to write an read will be mostly hidden in a coding box. And thinking about it made me realize that soon there will be a completely different programming language…
1. Constitution can't work without punitive enforcement, how will you punish agent/LLM? 2. Even if we can enforce laws for agents/LLM, just look at existing law system it is tug of war because we almost can't write…
Well, even without that AI can do human engineering and fishing or outright blackmail to get what they want from labs and government officials.
I have started with generating very detailed "feature" spec and going over it many times until it looked good to me. Then I made it write an "architecture doc" and plan how to implement all which was about 15 parts.…
I've been making a macos app with opus 4.8-5 and at first it was great, everything materialized in a week, but when I started tuning stuff and fixing performance problems I have spent a very frustrating month…
I had a genius response from Claude recently after asking how can it be marketed as smart and "almost AGI" despite being so stupid: "I compress the labour. Not the responsibility."
That can be true. On multiple occasions when claude did some BS I have asked it why and it explained that it is optimizing for task completion and not for communication.
I have a rule in claude.md: ``` ## Writing rules *Describe the code as it is now — no residue, no change-narration.* Artifacts (docs, plans, comments, commit messages) should describe the current code statically, as if…
It is sufficient not at all
Yeah, I should probably /clear more often. Compaction seem cheap by itself (all cached input and small output), but it often marks unnecessary files for pre-load.
Many very well made software written without any AI was never "shipped" because there were no people who wanted to pay for it, many very poorly made software was shipped because demand and marketing did the job. So…
I've actually found that compacting as often as possible, after planning, then between each implementation step works the best, it both unloads unnecessary context of previous edits and test runs, makes thinking…
My experience as well, I've been developing a native macos app using CC. As a web dev I didn't know much about the stack. Nothing too fancy a kind of folder gallery-player with tags embedded in filenames, a bit like…
I think it case of coding it may not be as bad, because new training data (AI generated code) is always empirically validated by tooling and by consumer. It may not be good but it mostly works, otherwise it is discarded…
So true. I am cloding a macos app (a domain I know little about), with Opus 4.8 xhigh, and it was glorious at first seeing the app materializing and working (notwithstanding tedious detailed feature spec write up), but…
I've made it write a /status-line thing to display context tokens in the status line and also a hook to stop and ask to continue or compact whenever it reaches 250k tokens. For subscription I have also made it stop at…
Many game ads on ios are already playable, I guess we're just one step away from what you describe.
> it has advanced significantly since early releases I have used Claude Code past few weeks and honestly can't tell if it is any better, or does anything different than Copilot in agent mode with same models.
I'd say it is quite opposite, a deep understanding of what you like and consequently understanding what will make a creation into exactly what you like. (Well I guess some people can create without understanding, just…
For me, even if I drop into "mental space" completely and stop seeing(or being aware of) real world while thinking about something I saw/did recently, vividness of this mental image will depend on how close I am to…
Good erotic literature does not only describe images, but also desires, emotions and sensations, all of which I think have different channels of imagination/recall.
For me visualization by itself is mostly useless, it is more of a concept of something arousing happening and vague visual flashes of something similar I have seen. It somewhat works, but nowhere near as effective as…
I feel like "intuition" really fits to what LLM does. From the input LLM intuitively produces some tokens/text. And "thinking" LLM essentially again just uses intuition on previously generated tokens which produces…
A bit sad that the language and framework so enjoyable to write an read will be mostly hidden in a coding box. And thinking about it made me realize that soon there will be a completely different programming language…