71–80 of 87 posts
Earlier quoted context omitted.
it's free code. if you're so concerned about the quality, you can read it yourself.
And if anyone is so put out by my suggestion (that I said I'd hold myself to as well), they can just ignore me and move on. I posted a comment on a public forum about what I'd like, I'm not the boss of anyone.
Earlier quoted context omitted.
What's the point? You can make good or bad software, with or without LLMs. Do you ask a carpenter if they use a hammer or nail gun? Did they only use the nail gun for the roof and the deck? If you care that much and don't have a foundation of trust, you need to either verify the construction is good, or build it yourself. Anything else is just wishful thinking.
It’s not all-or-nothing: a statement like what I want would be part of the assurance, not the whole thing.
If you want assurance, look for other signals IMHO.
I clicked this thinking “oh, cool, someone finally made a portable version of the Claude.ai* memory system!” Spoiler, no, it’s not it at all, it’s just a “store”/“remember” memory system… as opposed to the Claude.ai memory system, where it doesn’t make the model actively have to write memories on its own, but rather has a model in the background go through your chat history and generate a summary from it. I’ve found…
I think with automatic creation you need async consolidation (calling it dreaming is a little dramatic for my taste).
My implementation is at Elroy.bot, I recently wrote about different approaches to agent memory here: https://tombedor.dev/approaches-to-agent-memory/
I clicked this thinking “oh, cool, someone finally made a portable version of the Claude.ai* memory system!” Spoiler, no, it’s not it at all, it’s just a “store”/“remember” memory system… as opposed to the Claude.ai memory system, where it doesn’t make the model actively have to write memories on its own, but rather has a model in the background go through your chat history and generate a summary from it. I’ve found…
That's an interesting concept. So it's like if you're an agent chatting with a user, you have an army of assistants who overhear the conversation and record important facts, or search relevant facts on some database and decide on the fly when to interrupt you with "this memory X looks relevant". Sounds easy enough if tokens were free, but an interesting problem to do it efficiently.
I still haven't found useful "memory". It's either an agents.md with a high level summary, which is fairly useless for specific details (eg "editing this element needs to mark this other element as a draft") or something detailed and explaining the nitty gritty, which seems to give too much detail such that it gets ignored, or detail from one functional area contaminates the intended changes in another functional are…
What you’re describing sounds more like code review guidelines, which can be explicitly brought into context at specific times during a change. A memory system is both too complex and less accurate for this
Earlier quoted context omitted.
And if anyone is so put out by my suggestion (that I said I'd hold myself to as well), they can just ignore me and move on. I posted a comment on a public forum about what I'd like, I'm not the boss of anyone.
There a huge difference between suggestions and demands. I posted a comment about the tone of your comment you can also ignore it.
Earlier quoted context omitted.
It’s not all-or-nothing: a statement like what I want would be part of the assurance, not the whole thing.
It's meaningless though. It's performative virtue signalling with no assurance. Some people will produce great/poor quality regardless of the tools used. For ever vibe coder barfing up spaghetti, there's an engineer using the same tools to enhance their craft. If you want assurance, look for other signals IMHO.
Earlier quoted context omitted.
It's meaningless though. It's performative virtue signalling with no assurance. Some people will produce great/poor quality regardless of the tools used. For ever vibe coder barfing up spaghetti, there's an engineer using the same tools to enhance their craft. If you want assurance, look for other signals IMHO.
Code quality is indeed a virtue that I would like signalled and partly assured, through the means of the author feeling the social pressure of performing an explanation of their use of LLMs, and wanting to not appear careless. In my direct experience, the way you use these tools has a big effect on the outcome, and that’s the information I’d like conveyed here. Clearly it doesn’t cover people who would have produced…
> it doesn’t cover people who would have produced rubbish anyway
How do you determine this though?
If it becomes common for people to include an AI usage profile, what does that really do? I can say I followed best practices, steered design, supervised the LLM, reviewed the code, etc... but those are just a stranger's words with little value, and my code might still be garbage.
Earlier quoted context omitted.
Code quality is indeed a virtue that I would like signalled and partly assured, through the means of the author feeling the social pressure of performing an explanation of their use of LLMs, and wanting to not appear careless. In my direct experience, the way you use these tools has a big effect on the outcome, and that’s the information I’d like conveyed here. Clearly it doesn’t cover people who would have produced…
Fair enough, we all have our preferences and opinions. What signals would you be looking for to make your judgement call? > it doesn’t cover people who would have produced rubbish anyway How do you determine this though? If it becomes common for people to include an AI usage profile, what does that really do? I can say I followed best practices, steered design, supervised the LLM, reviewed the code, etc... but those…
Earlier quoted context omitted.
Code quality is indeed a virtue that I would like signalled and partly assured, through the means of the author feeling the social pressure of performing an explanation of their use of LLMs, and wanting to not appear careless. In my direct experience, the way you use these tools has a big effect on the outcome, and that’s the information I’d like conveyed here. Clearly it doesn’t cover people who would have produced…
Fair enough, we all have our preferences and opinions. What signals would you be looking for to make your judgement call? > it doesn’t cover people who would have produced rubbish anyway How do you determine this though? If it becomes common for people to include an AI usage profile, what does that really do? I can say I followed best practices, steered design, supervised the LLM, reviewed the code, etc... but those…