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

271–280 of 391 posts

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

#271

Post by trueno »

jp57 wrote: post #115
MisterMunchkin wrote: post #94

Earlier quoted context omitted.

They've corrupted their data set by padding it with generated slop, in the misguided belief that you need 10PB of data to train a brain. Every training round they load more AI slop into it, further amplifying the slop language. It's fascinating, Sonnet 4 is still available via API and it's so much less moronic than the current model. All of the em-dashes and nonsense are a result of the repeated rounds of reinforceme…

But why did that style of writing get rewarded? The people at Anthropic are ultimately responsible for the reward signal and what it produced.

i think they took a bet that TED talk style chat would make their AI offering feel like the better offering. they didn't anticipate that it would become a meme. because of course they didn't, what a stupid idea to train around and reward in the training. you gotta be smoking real delusion to think that was going to be a game changing feature. at work we even got non-technical people making fun of it like crazy now.

going back to opus 4.8 and on is literally like talking to the guy who wants to hear his own voice in meetings. going back to 4.6 is actually refreshing, and it feels so much faster. actually gonna laugh if 4.8 and on is so slow because it's draining lakes fighting for its life trying to conjure up this god forsaken persona.

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

#272

Post by kyleee »

monkpit wrote: post #265
easterncalculus wrote: post #236

Earlier quoted context omitted.

It's bad enough from Opus, but it's worse how people have actually retooled their vocabulary around these tools. In the US tech industry, at least.

Have people done that? Or are they just meat puppets?

Do the needful please and reconsider your comment

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

#273

Post by nojs »

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 suspect it’s a side effect of heavy RL that rewards solved problems but not writing clarity.

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

#274

Post by GMoromisato »

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…

> Has it been imprinted with Dario's engrams?

I understood that reference!

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

#276

Post by josh_p »

hacker_homie wrote: post #275

Skills still confuse me, why isn't this just a repo with a single md file. why does it need js to load a md file.

It mostly doesn't depending on the harness you're using the skill with. The author turned it into a pi extension, for example, in the `extensions` folder in the repo. Users of pi can enable and disable the skill with a slash command. I saw some other harnesses supported.

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

#277

Post by recursivecaveat »

nojs wrote: post #273
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 suspect it’s a side effect of heavy RL that rewards solved problems but not writing clarity.

With human RL, sounding like you've solved a problem is even better. So many times Codex writes some enthusiastic paragraph, then I learn later that it never reran the tests, or had to add some insane hard-coded hack that renders the feature useless for the general case, etc.

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

#278

Post by idontwantthis »

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 did add that rule and it’s helped a lot. It greps for ways it writes negative statements and does a pass to correct them. I can’t get it to stop writing them in the first place though.

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

#279

Post by wolvoleo »

adaml_623 wrote: post #234
krustyburger wrote: post #98

Earlier quoted context omitted.

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?

Potpourri is an excellent word to describe LLM output

I love that description. It matches very well what I feel about LLM output. This overly sweet scented smell meant to cover up something nasty, with a strong artificial tint to it.

Which doesn't say that much about the LLM itself but about the people that make the training material.

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

#280

Post by rurban »

1659447091 wrote: post #160
krustyburger wrote: post #98

Earlier quoted context omitted.

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?

yes continue

.
Post reply on HN