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

281–290 of 393 posts

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

#281

Post by hysan »

vzmax wrote: post #161
hysan wrote: post #120

Earlier quoted context omitted.

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.

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 in the model. Over the 30+ sessions where I’ve tried this, the overwhelming claim was some variant of a harness instruction. It might not be there but given the consistency and how all my rule tests have failed in the same way that others describe, it at least makes it reasonable to conclude that it’s baked in somewhere and in a way where agent rules aren’t able to strongly affect the behavior. My bet would be on the harness because the class of undesired behavior follows that of a structured response.

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

#282

Post by Plont »

kube-system wrote: post #131
idicjeifjwjd wrote: post #97

Earlier quoted context omitted.

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.

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".

That's exactly the problem though; humans will anthropomorphize everything from a roomba to a rock as it is. We're weak to this. We evolved in environments where looking for and recognizing real animals and humans was vital for survival, and false positives were relatively harmless. (Or potentially sometimes even helpful, like in the case of stuffed animals providing comfort to children.)

Now we have this software that's specifically designed to mimic humans, and mistaking it for real intelligence or consciousness can easily be disastrous. It's very important that we not anthropomorphize it, but we are catastrophically bad at NOT doing that.

Even our language has had a lot of computer anthropomorphism baked into it ("my phone died!", "this laptop is fussy", "the computer is sleeping", "it's thinking"), and it's not easy to excise that routine anthropomorphism from the way we talk about LLMs.

I don't want an LLM to write as if it were a person because it's definitely easier and more reliable to cut that problem off at the root, as much as possible, rather than to just try to willpower my way out of my human tendency to anthropomorphize inanimate objects.

I'll grant that LLMs talk like this because they're trained on human writing. It may not be possible to get them to not do that. But if it can't be fixed, it's just another thing to put on the "reasons this is all an incredibly stupid idea" pile.

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

#284

Post by jppittma »

mcv wrote: post #197
vzmax wrote: post #161

Earlier 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.

To me it explained its inability to follow my preferred coding style by blaming its training data.

I've had better success with having it write and then rewrite rather than trying to prompt the first write into following my style rules.

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

#285

Post by amazingman »

alwillis wrote: post #56
amazingman wrote: post #48

Earlier quoted context omitted.

I have found both hyperfocus and the ability to quickly "drop" (i.e. distract from) a train of thought incredibly useful.

Hyperfocus is great until it's not. People with ADHD have "time blindness"; we don't process time the same way most people do. We often don't realize 3 or 4 hours have passed and there were other things we needed to get done.

Sure. These are the other sides of the coin. I've been medicated for years and unmedicated for years. Currently I'm in a ~10yr unmedicated stretch. Do I have frustrating moments, embarrassing easily avoidable failures, and so on? Yes. Do I sometimes lose many hours to a task and forget to eat? Yes. But I'm also kinder, more playful, and more present with my loved ones when I am unmedicated.

If the downsides get too bad and things start to fall apart then I will medicate again. Until then, no way I'm making that tradeoff.

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

#286

Post by tough »

jppittma wrote: post #284
mcv wrote: post #197

Earlier quoted context omitted.

To me it explained its inability to follow my preferred coding style by blaming its training data.

I've had better success with having it write and then rewrite rather than trying to prompt the first write into following my style rules.

also by abusing linters and other guardrails you can basically automate the rewrite

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

#287

Post by tough »

kdkdkwndjekd wrote: post #196
throwawayk7h wrote: post #162

Earlier quoted context omitted.

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.

Except in this case this makes 0 sense since AIs are sycophantic by nature. You tell it to do something and it just does it. If it can burn tokens trying to sound more human (which is programmed in, not a byproduct), then it can very well just not do that and get on with the work. Impersonating a human does nothing to help it solve problems faster, quite the contrary in fact, it has to waste even more time coming up…

Have you ever heard of Chain of Thought?

Might want to rethink your statement after going again through what it does exactly. No need to sound more human. but it gives more tokens to "think" like a human committing brain-time to a problem would

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

#289

Post by wiseowise »

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).

Finally. It is scary that this is not the top comment in the thread.

The “I can’t bother to read a paragraph therefore ADHD lolzzz” crowd is really fucking annoying.

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

#290

Post by wiseowise »

spicyusername wrote: post #11
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 mean... like most spectrum disorders, most people experience and can relate to at least some of the core symptoms, even if they don't express the full spectrum or severity. So when someone says they feel like they have ADHD, they are probably not inaccurate.

You know what other thing that those with this fake ADHD can also relate to? Wasting hours a day scrolling on garbage resources.
Post reply on HN