Earlier quoted context omitted.
[flagged]
Your HN comment is not useful. If you think it is, then you're suffering from HN psychosis.
[flagged]
I-have-ADHD: A skill to stop coding agents from burying the answer
361–370 of 395 posts
Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#362Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#363[flagged]
Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#364Earlier quoted context omitted.
You can't trust it's account on why it did something, it does not "remember". It will just make up something plausible sounding.
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 i…
Meta:
> 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 worthless...
Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#365I am [undiagnosed] high-functioning ASD Level 1, I have high "intelligence" and very strong pattern recognition but slow "processing speed". As a result I am quickly overwhelmed by having too much information presented at once; when presented with lots of "threads" my brain tries to follow them all at once and just melts down.
As a result, Claude's default behavior (as a coding agent) is basically engineered to slow me down. Skills like this definitely help, to the extent that the agent respects them as context grows.
Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#366Earlier quoted context omitted.
You can't trust it's account on why it did something, it does not "remember". It will just make up something plausible sounding.
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, becaus…
Is there a way to dump the state directly?
Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#367Personally I ask it to explain it simply like it’s talking to an executive reading it on their phone while on another meeting.
Haha, thanks I'll try this. I typically tell it to explain in one of the following ways:
- as the grug brained developer
- for smoothbrains
- for high school reading level intern
- in the style of Samuel L. JacksonRe: I-have-ADHD: A skill to stop coding agents from burying the answer
#368Earlier quoted context omitted.
[flagged]
100% sentences like i convinced it or made it admit are just weird But how else to describe the situation
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.
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.
Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#369Re: I-have-ADHD: A skill to stop coding agents from burying the answer
#370Let'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 Anth…
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" issue…
I could also replace the system prompt (eg using a different harness) to achieve a similar result yes?