I did the same in about the same timeframe. I created a nice little hierarchy of "when writing tests, read docs/test-patterns.md" type logic. The idea was to put all of my personal heuristics about coding in a "lazy…
I didn't think it was that controversial actually. I don't bother navigating man pages or help FAQs anymore, i just ask the agent how do i do X step by step. Opening this up as part of the app to regular non-engineering…
My hypothesis is that the help/support buttons in nearly all apps will be to an agent in the future. Like now you would type "how do i do X" in the excel search bar, in the future it will be "do x". Users in 10 years…
I tried both --system-prompt and --system-prompt-file. they both appended when i tried about 6 months ago and watched the traffic. Yes I cleanup all those tools etc.
there is literally a --system-prompt flag for claude code. In my mitmproxy experiments using that flag appended to the existing system prompt rather than replacing it. So I had to create a little helper to strip the…
FYI you can modify the system prompt using mitmproxy. Just ask your agent to walk you through it. Anthropic system prompts are gnarly and geared towards the lowest common denominator.
this ticks at something that maybe is obvious in retrospect- this is all about economics. the arguments about "using AI doesn't make you an artist", etc. are about being able to charge money for your art i think. maybe…
i disable subagents. it also helps that i work in microservice size repos, so a single agent can keep the full relevant context. subagents waste alot of unnecessary tokens doing code exploration that the main agent is…
I appreciate you directly addressing what I was talking about. In my case, I'm an old school 90s wannabe rapper/producer and I used to make beats with old school drum machines, a sequential prophet 2000 sampler, and my…
I've been on this kick since I realized the primacy of the initial part of the session context. I created a python app that reads a phased plan and kicks off a new session for each phase. There is a standard prompt and…
I mean i suppose it depends on if you think people using blender are artists. If you think the part that makes them creative is knowing to right click select blah do blah then I get your position. If you say "no, make…
you don't need to learn blender anymore. you can talk with the ai and describe what you want and iterate. all of the software tools used in media are now accessible to creative but not necessarily technical people.
The system reminder explicitly tells it that the CLAUDE.md or AGENTS.md content is optional. I believe this is a big part of why CC doesn't heed the instructions alot of the time: IMPORTANT: this context may or may not…
Claude Code wraps both the AGENTS.md and CLAUDE.md in a system-reminder with this disclaimer at the bottom: IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless…
I am curious if we will reach a point where people who are skilled at context engineering/architecture eventually are hired to do jobs completely out of their fields. I think the best pairing would be domain experts +…
totally agree with the repo idea. working with AI in a git repo and allowing it to write markdown files it slowly builds context over time. i knew a guy who had been using the same session for weeks because he felt he…
this is a great way of expressing it.
i asked opus 4.5 what the problem was and it said it pattern matched too much. i asked it how it should do it, it wrote a file that told itself to stop pattern matching. it wrote a file that started with the following…
I got pretty good mileage out of context engineering, adding my personal coding heuristics to my AGENTS.md and referencing subdocuments on a "when doing X, consult Y" pattern. I assume others are doing similar things,…
I use the AGENTS.md to show it how i want the code to look like. Something like "when implementing hooks adhere to the guidelines in docs/react-hooks.md". And then react-hooks describes your heuristics and what you…
I was pleasantly surprised to find that the GPT models are much stricter in adhering to my AGENTS.md guidelines and heuristics than Claude.
I feel like this is relevant to the takes of "ai psychosis". I spent about 600 hours working alone with AI before I was ready to collaborate, re-discovering things in my own process that others may have already known…
I mean, not to be flippant but can't you just prompt the agent to write a file as you're getting closer to the compaction limit? I tend to just go to roughly 50-70% context utilization and then tell the agent to…
I agree it doesn't make the capabilities infinitely scalable, wasn't arguing with that point. It's just an experiment. I'm not talking about "you are an expert mathematician, go", I'm talking about an expert encoding…
likewise, the opening to Comfortably Numb always resonates.
I did the same in about the same timeframe. I created a nice little hierarchy of "when writing tests, read docs/test-patterns.md" type logic. The idea was to put all of my personal heuristics about coding in a "lazy…
I didn't think it was that controversial actually. I don't bother navigating man pages or help FAQs anymore, i just ask the agent how do i do X step by step. Opening this up as part of the app to regular non-engineering…
My hypothesis is that the help/support buttons in nearly all apps will be to an agent in the future. Like now you would type "how do i do X" in the excel search bar, in the future it will be "do x". Users in 10 years…
I tried both --system-prompt and --system-prompt-file. they both appended when i tried about 6 months ago and watched the traffic. Yes I cleanup all those tools etc.
there is literally a --system-prompt flag for claude code. In my mitmproxy experiments using that flag appended to the existing system prompt rather than replacing it. So I had to create a little helper to strip the…
FYI you can modify the system prompt using mitmproxy. Just ask your agent to walk you through it. Anthropic system prompts are gnarly and geared towards the lowest common denominator.
this ticks at something that maybe is obvious in retrospect- this is all about economics. the arguments about "using AI doesn't make you an artist", etc. are about being able to charge money for your art i think. maybe…
i disable subagents. it also helps that i work in microservice size repos, so a single agent can keep the full relevant context. subagents waste alot of unnecessary tokens doing code exploration that the main agent is…
I appreciate you directly addressing what I was talking about. In my case, I'm an old school 90s wannabe rapper/producer and I used to make beats with old school drum machines, a sequential prophet 2000 sampler, and my…
I've been on this kick since I realized the primacy of the initial part of the session context. I created a python app that reads a phased plan and kicks off a new session for each phase. There is a standard prompt and…
I mean i suppose it depends on if you think people using blender are artists. If you think the part that makes them creative is knowing to right click select blah do blah then I get your position. If you say "no, make…
you don't need to learn blender anymore. you can talk with the ai and describe what you want and iterate. all of the software tools used in media are now accessible to creative but not necessarily technical people.
The system reminder explicitly tells it that the CLAUDE.md or AGENTS.md content is optional. I believe this is a big part of why CC doesn't heed the instructions alot of the time: IMPORTANT: this context may or may not…
Claude Code wraps both the AGENTS.md and CLAUDE.md in a system-reminder with this disclaimer at the bottom: IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless…
I am curious if we will reach a point where people who are skilled at context engineering/architecture eventually are hired to do jobs completely out of their fields. I think the best pairing would be domain experts +…
totally agree with the repo idea. working with AI in a git repo and allowing it to write markdown files it slowly builds context over time. i knew a guy who had been using the same session for weeks because he felt he…
this is a great way of expressing it.
i asked opus 4.5 what the problem was and it said it pattern matched too much. i asked it how it should do it, it wrote a file that told itself to stop pattern matching. it wrote a file that started with the following…
I got pretty good mileage out of context engineering, adding my personal coding heuristics to my AGENTS.md and referencing subdocuments on a "when doing X, consult Y" pattern. I assume others are doing similar things,…
I use the AGENTS.md to show it how i want the code to look like. Something like "when implementing hooks adhere to the guidelines in docs/react-hooks.md". And then react-hooks describes your heuristics and what you…
I was pleasantly surprised to find that the GPT models are much stricter in adhering to my AGENTS.md guidelines and heuristics than Claude.
I feel like this is relevant to the takes of "ai psychosis". I spent about 600 hours working alone with AI before I was ready to collaborate, re-discovering things in my own process that others may have already known…
I mean, not to be flippant but can't you just prompt the agent to write a file as you're getting closer to the compaction limit? I tend to just go to roughly 50-70% context utilization and then tell the agent to…
I agree it doesn't make the capabilities infinitely scalable, wasn't arguing with that point. It's just an experiment. I'm not talking about "you are an expert mathematician, go", I'm talking about an expert encoding…
likewise, the opening to Comfortably Numb always resonates.