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

201–210 of 389 posts

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

#201

Post by EdwardDiego »

krustyburger wrote: post #98
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…

Not just imprinted with the engrams of any one person (however brilliant they might be) — it’s more than that! Like all great writing, it’s more like it’s been imbued with patterns, patterns that are peppered with a potpourri of popular ways of writing in an enthusiastic style while regularly restating things and recapitulating them. Would you like me to explain more?

I would like to know more. (Wait, I'm mixing my memes)

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

#202

Post by NewJazz »

al_borland wrote: post #198

I’ve been scolding my LLM quite a bit lately for this. Instead of telling me what to do, it first tells me 3 ways that might technically work, but I probably shouldn’t use for various reasons. This is all a waste of my time, tokens, and sanity.

They bill per token, what do you expect?

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

#203

Post by phainopepla2 »

LollipopYakuza wrote: post #57
phainopepla2 wrote: post #34

Earlier quoted context omitted.

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

I would sum it up as an ability to think out of the box, naturally having creative solutions. Which itself is a double-edged sword...

I know a lot of people with ADHD and even more without it. I haven't noticed any correlation between ADHD and creativity or out-of-the-box thinking.

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

#204

Post by corford »

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…

After some iteration, this is what I currently shove in every AGENTS.md to make Fable legible:

## Writing guidelines

These apply to documentation, code comments, commit and PR messages, and replies to the user.

- Write precisely in clear, complete sentences; keep text concise and proportional to task complexity.

- Stay focused: avoid filler, repetition, over-the-top detail, and tangents the user did not ask for. Once a fact is stated, do not restate it for effect ("so the commit landed on a branch nobody was going to merge"). Do not editorialise.

- Always prefer ISO 24495-1:2023 conformant plain language over dense technical jargon: short sentences, one idea per sentence, define terms on first use.

- When reporting your own mistake, give the cause and the fix in one sentence each; no apology, no framing ("the mistake was mine"), no post-mortem.

- Never use em dashes or cataphoric teasers such as "Here's the thing" or "But there's a catch".

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

#205

Post by procone »

kdkdkwndjekd wrote: post #194
kube-system wrote: post #131

Earlier quoted context omitted.

You're anthropomorphizing in the same breath that you criticize anthropomorphism. Claude predicts the next token of the predominantly human training input, and humans use "I".

> You're anthropomorphizing in the same breath that you criticize anthropomorphism. Nice attempt at a “aha, gotcha!” comment, but sadly you’re too off-mark for it to work. > Claude predicts the next token of the predominantly human training input, and humans use "I". This is inconsequential. It could very well be programmed to not assume such a personified stance, and yet here we are. Nothing you do makes it drop thi…

Is this a troll post? Claude is not "programmed" at all.

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

#207

Post by voiceeh »

cyanydeez wrote: post #171
saghm wrote: post #112

Earlier quoted context omitted.

You think that they communicate? I just assumed they sent each other output of Claude, which is then fed into Claude

why even copy-paste when you can just plug the two terminals together and observe like fish; then just occasionally sprinkle in the flakes. Isn't that the idea here, just stop being people.

I did this, kind of, with my companies internal tools. LLMLLM links.

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

#208

Post by kdkdkwndjekd »

procone wrote: post #205
kdkdkwndjekd wrote: post #194

Earlier quoted context omitted.

> You're anthropomorphizing in the same breath that you criticize anthropomorphism. Nice attempt at a “aha, gotcha!” comment, but sadly you’re too off-mark for it to work. > Claude predicts the next token of the predominantly human training input, and humans use "I". This is inconsequential. It could very well be programmed to not assume such a personified stance, and yet here we are. Nothing you do makes it drop thi…

Is this a troll post? Claude is not "programmed" at all.

> Is this a troll post? Claude is not "programmed" at all.

I could ask you the same. Are you trying to say AIs cannot be made to prefer behaving in certain ways? Because if so, I’ve got a bridge to sell you.

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

#209

Post by TomGarden »

larodi wrote: post #166
TomGarden wrote: post #143

Earlier quoted context omitted.

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.

Yeah agree. Someone on HN posed the theory that the dogfooding might have worked against them here - the theory is that internally they used Fable as conversational agent and Opus as subagents, leading to Opus falling deeper into a style mainly aimed at other LLMs.

All conjecture of course, and yeah it's hard to imagine they would enjoy this prose internally

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

#210

Post by code_biologist »

mjsarfatti wrote: post #137

You don’t need a skill. Just tell it to BLUF (bottom line up front) and ASD-STE100. And stop using Opus 9 Pro Max XHigh 10.0 for everything. If you choose a hyper-thinking model for asking the weather you can’t but expect yapping.

There's no physical reason "smartest/most capable model" should be "most yappy model". Smart people can write concisely. It's unfortunate you have to tolerate/fight yappiness to get intelligence with current SotA models.
Post reply on HN