Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I-have-ADHD: A skill to stop coding agents from burying the answer

github.com

Post reply on HN
Print view View original

71–80 of 390 posts

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#71

Post by jp57 »

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?

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#72

Post by nosmokewhereiam »

phishin wrote: post #21
egeozcan wrote: post #8

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).

I have it and it is absolute gift that I wouldn’t trade for anything. It has taken years to figure how to harness it though.

...you don't have it.

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#73

Post by soontimes »

sleazebreeze wrote: post #12

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…

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

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#74

Post by ryandrake »

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'."

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#75

Post by nedomolkovivan »

sleazebreeze wrote: post #12

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…

[flagged]

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#76

Post by eterm »

ryandrake wrote: post #74

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 t…

I've found it does this in two situations:

Firstly when you've instructed it ( possibly through skills ) not to do something. It'll keep reminding you that it didn't do that. So I might say, "Check out and review this PR, do not make comments on it", and then it'll be keen to point out it hasn't posted comments to the PR.

But more often it happens when it tries one approach, gets itself messed up, and then has to back out that approach, clean up its mess and do something else.

It'll often then spend more time explaining the wrong approach than the right one, which can be frustrating, especially if all its working is buried in the detailed transcripts.

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#77

Post by heyiammallik »

I like the problem this is trying to solve. One thing I'm not sure about though is whether this kind of a preference should be a skill at all.

Stuff like put the answer first, don't bury the useful bit etc feel like user level preferences that should survive across tasks. Agents.md is repo context, skills are useful when a particular task needs extra instructions but this is neither really.

Right now we seem to be stuffing all 3 kinds of things into context hoping model pays attention to it where needed as session grows. Also +1 on not making this purely about shorter output

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#78

Post by nzach »

ryandrake wrote: post #74

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 t…

My guess would be that somewhere you have these instructions being fed to the agent. Double check skills, AGENTS.md, memory, agent definition...

You can also ask why did he mentioned something that wasn't done or why he thought this was important.

In my AGENTS.md file I have an instruction telling the agent to never commit any changes unless I explicitly ask for it, and this leads to messages similar to what you just described.

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#79

Post by jolt42 »

ryandrake wrote: post #74

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 t…

That wouldn't bother me if it would just make bullet lists, which I think I'll start asking for. "Summarize", "synopsis", "brief", "concise" these rarely help I feel because its summarizing noise as well.
Post reply on HN