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

161–170 of 384 posts

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

#161

Post by vzmax »

hysan wrote: post #120
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…

Relevant anecdata because I've burned many a Claude sessions on this. If you're using Claude Code, then it's in the harness. At the close of many sessions, I would start a meta conversation over why the LLM would consistently break certain rules. What it found when debugging itself is that some of the "contradicting" rules that I had were in fact, not from my rules. Instead, the instructions from its own harness had…

You can't trust it's account on why it did something, it does not "remember". It will just make up something plausible sounding.

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

#162

Post by throwawayk7h »

idicjeifjwjd wrote: post #97
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…

The thing I struggle the most with is getting it to stop referring to itself with personal pronouns. No Claude, you are not an “I” you are an “it”. You are a fucking tool, dammit. Tell me what you did without trying to assume personality; stop impersonating humans you steroidal autocorrect.

I imagine that, corpus aside, it uses personal pronouns for much the same reason that humans do. It's useful for it to have a self-referential vector embedding, and this lets it solve problems faster and more efficiently.

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

#163

Post by JesseTG »

8cvor6j844qw_d6 wrote: post #92
bgilroy26 wrote: post #83

Earlier quoted context omitted.

You've identified a load-bearing problem and it's worth naming

You're absolutely right, and I think you've put your finger on something important here. That said, I think there's a deeper tension here that's worth naming.

This thread is giving me a load-bearing aneurysm.

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

#164

Post by 98codes »

phainopepla2 wrote: post #34
phishin wrote: post #21

Earlier quoted context omitted.

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.

Can you explain what about is it a gift? What are the benefits you get from it?

When you can align hyperfocus with your most beneficial vector of productivity, it's like you can accomplish anything, in half the time thought possible.

Problem is, there is no good way to direct the hyperfocus demon. It likes what it likes, it wants what it wants, and that's that.

Medication helps to save a pile of willpower/spoons/executive function safely from the demon so that we can get things that need doing done.

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

#165

Post by infogulch »

jp57 wrote: post #71

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 Anth…

Can we imprint Claude with a little more Antoine de Saint-Exupéry:

> Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away.

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

#166

Post by larodi »

TomGarden wrote: post #143
jp57 wrote: post #71

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 Anth…

It seems they are taking it seriously now - Boris et al have been mentioning they are working on a fix and shipped a temporary band-aid output style to combat Opus 5's horrendous prose. We'll see if they can do it, I originally got into Claude Code because it, at the time, felt more accessible/conversational than Codex/Gemini. Now it's shifted to say the least

They seem to have been rushed with certain releases. It is impossible they didn’t know or see this awful writing before 5 series.

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

#168

Post by cromka »

jp57 wrote: post #71

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 Anth…

I was incredibly surprised how much better was Astra at rephrasing the docs that Fable came up for a project I am about to publish. The instructions are now actually what a human would expect, with clear logic flow diagrams, lists itemized, short paragraphs. It also actually correctly detected the train-of-thought leftovers, as well as stuff that never made it to final version of the project and removed them.

Meanwhile Fable consistently ignores all my requests to write this exact way. I mean, the bare minimum I ask it for it to itemize lists and not write in single long passages using comas, semicolons and 'and's. Still ignores them.

I honestly think it's time to call Astra the SOTA. It may not lead all the benchmarks but it genuinely feels much superior of a model. Not to mention the ¢20 Codex plan with frequent resets (https://codex-resets.com/) gives me roughly as much allowance as the ¢90 Claude plan, especially with recent limit cuts on Anthropic plans.

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

#169

Post by mattjoyce »

jmartrican wrote: post #133
KronisLV wrote: post #130

Earlier quoted context omitted.

It was quite insufferable: https://blog.kronis.dev/blog/ai-slop-is-a-self-inflicted-tra... Long story short, I ended up looking at other providers and models like Kimi K3 and GLM 5.3 and eventually just stuck with OpenAI (more limits, despite smaller context), none of them have such pronounced issues with the tone and writing like Claude does - seems like they were working on it with 5.1 but I'd almost classify it as…

I imagine Claudisms might make it into human-speak.

You're absolutely right.
Post reply on HN