Hacker News: dontlikeyoueith

New comment by dontlikeyoueith in "The M×N problem of tool calling and open-source models"

dontlikeyoueith — Tue, 14 Apr 2026 17:22:13 +0000

> LLMs are based on neural networks, so one could create an interface where activating certain neurons triggers tool calls, with other neurons encoding the inputs; another set of neurons could be triggered by the tokenized result from the tool call.

You can do this. It's just sticking a different classifier head on top of the model.

Before foundation models it was a standard Deep RL approach. It probably still is within that space (I haven't kept up on the research).

You don't hear about it here because if you do that then every use case needs a custom classifier head which needs to be trained on data for that use case. It negates the "single model you can use for lots of things" benefit of LLMs.

New comment by dontlikeyoueith in "GitHub Stacked PRs"

dontlikeyoueith — Tue, 14 Apr 2026 17:17:15 +0000

> I think the point the GP was trying to make is that the GitHub UI ought to be able to allow you to submit a branch with multiple well-organized commits and review each commit separately with its own PR

So the point he's trying to make is that Gituhub UI should support Stacked PRs but call them something else because he doesn't like the name?

New comment by dontlikeyoueith in "GitHub Stacked PRs"

dontlikeyoueith — Tue, 14 Apr 2026 17:10:31 +0000

Why do you insist on a different but functionally equivalent solution to the problem?

It's weird.

> Why do we tolerate the fact that GitHub doesn't let you say "approved for changes in `frontend/*`

That's literally what stacked PRs are adding.

New comment by dontlikeyoueith in "GitHub Stacked PRs"

dontlikeyoueith — Tue, 14 Apr 2026 16:50:31 +0000

Depends on what you consider long-lived.

I typically generate stacks of 3-5 PRs in 1-2 days now (in a gen-AI world).

New comment by dontlikeyoueith in "GitHub Stacked PRs"

dontlikeyoueith — Tue, 14 Apr 2026 16:48:15 +0000

Because sometimes there are changes that need to land as all or nothing.

New comment by dontlikeyoueith in "Chimpanzees in Uganda locked in eight-year 'civil war', say researchers"

dontlikeyoueith — Fri, 10 Apr 2026 22:43:57 +0000

> When competing for resources, killing your neighbour frees up resources, which you can take. Most species of animal and even plants do this to some extent.

If anything, I'd say plants do it more. Everything in the garden is trying to kill everything else.

New comment by dontlikeyoueith in "Nowhere is safe"

dontlikeyoueith — Fri, 10 Apr 2026 22:40:50 +0000

There's been a massive step change in their capability per unit cost.

What used to cost millions per unit now costs tens of thousands. That's significant.

It's like saying artillery isn't that big a deal in 1914. After all, it's been around since 1452.

New comment by dontlikeyoueith in "F-15E jet shot down over Iran"

dontlikeyoueith — Fri, 03 Apr 2026 22:12:30 +0000

> Catering to their loudest supporters

Name one instance of this actually happening. I'll wait.

New comment by dontlikeyoueith in "The case for zero-error horizons in trustworthy LLMs"

dontlikeyoueith — Fri, 03 Apr 2026 02:03:05 +0000

Calling "reasoning tokens" "thinking" is a complete confusion of concepts on your part.

New comment by dontlikeyoueith in "The case for zero-error horizons in trustworthy LLMs"

dontlikeyoueith — Thu, 02 Apr 2026 17:32:30 +0000

Nope.

It's only surprising to people who still think they're going to build God out of LLMs.

New comment by dontlikeyoueith in "The Los Angeles Aqueduct Is Wild"

dontlikeyoueith — Fri, 20 Mar 2026 20:26:43 +0000

No, it's significantly more complex.

New comment by dontlikeyoueith in "The Los Angeles Aqueduct Is Wild"

dontlikeyoueith — Fri, 20 Mar 2026 20:23:57 +0000

They are referring to Hetch Hetchy.

New comment by dontlikeyoueith in "Sugar industry influenced researchers and blamed fat for CVD (2016)"

dontlikeyoueith — Fri, 09 Jan 2026 21:06:16 +0000

How about critiquing the actual recommendation instead of the people?

New comment by dontlikeyoueith in "Thousands of U.S. farmers have Parkinson's. They blame a deadly pesticide"

dontlikeyoueith — Mon, 15 Dec 2025 17:57:12 +0000

Too bad they voted to eliminate accountability for businesses that poison people.

Now they get to find out.

New comment by dontlikeyoueith in "Roomba maker goes bankrupt, Chinese owner emerges"

dontlikeyoueith — Mon, 15 Dec 2025 17:48:33 +0000

I have a Miele canister vacuum. I love it.

My wife bought the Dyson garbage anyway because she can't ignore her instagram feed.

New comment by dontlikeyoueith in "GPT-5.2"

dontlikeyoueith — Fri, 12 Dec 2025 17:09:27 +0000

> Refuse to express uncertainty or nuance (i asked ChatGPT to give me certainty %s which it did for a while but then just forgot...?)

They're literally incapable of this. Any number they give you is bullshit.

New comment by dontlikeyoueith in "The "confident idiot" problem: Why AI needs hard rules, not vibe checks"

dontlikeyoueith — Wed, 10 Dec 2025 01:51:17 +0000

You're hallucinating things I did not say.

New comment by dontlikeyoueith in "AI should only run as fast as we can catch up"

dontlikeyoueith — Tue, 09 Dec 2025 19:39:22 +0000

You're entitled to be wrong.

New comment by dontlikeyoueith in "The "confident idiot" problem: Why AI needs hard rules, not vibe checks"

dontlikeyoueith — Tue, 09 Dec 2025 19:36:47 +0000

Cute straw man.

You must be a CEO.

I'm not arguing anything. I'm observing reality. You're the one who is desperate to rationalize it.

New comment by dontlikeyoueith in "The "confident idiot" problem: Why AI needs hard rules, not vibe checks"

dontlikeyoueith — Tue, 09 Dec 2025 01:39:29 +0000

Yes, that is in fact their revealed preference.

Did you have a point?