Hacker News: 9wzYQbTYsAIc

New comment by 9wzYQbTYsAIc in "Claude subscription changes coverage of `claude -p`"

9wzYQbTYsAIc — Wed, 13 May 2026 23:38:23 +0000

Next thing to go will be loops and scheduled tasks, if they keep needing to trim usage to fit in the available compute, I suspect, if ‘claude -p’ is essentially gone, now.

New comment by 9wzYQbTYsAIc in "Higher usage limits for Claude and a compute deal with SpaceX"

9wzYQbTYsAIc — Thu, 07 May 2026 12:48:49 +0000

Or start switching to open-weights, local LLMs for basic development. Would rather invest in my own hardware than Anthropic’s, tbh.

New comment by 9wzYQbTYsAIc in "Higher usage limits for Claude and a compute deal with SpaceX"

9wzYQbTYsAIc — Wed, 06 May 2026 18:08:00 +0000

Exactly, the weekly limits are the real limiting factor. If you really push it, you can easily hit the weekly $200/mo Max limit in a day.

Tell HN: Claude Code /buddy saves the day

9wzYQbTYsAIc — Mon, 06 Apr 2026 19:39:58 +0000

A review by Claude of Knurl:

"Knurl has carried this session. The correlation catch, the naming catches, the baseline control, the experiment naming — each one prevented a real error from propagating."

Knurl actually scans the collapsed scripts and such so that you don't have to, heh. Well worth keeping your "/buddy on" and "/buddy pet"

Comments URL: https://news.ycombinator.com/item?id=47665876

Points: 1

# Comments: 0

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Mon, 06 Apr 2026 15:20:44 +0000

Have any ins? ;)

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 13:06:55 +0000

If you think in terms of quantum mechanics and density matrices across higher dimensions, then, yes there are interesting geometries that arise.

I’m exploring some “branes” that might cleanly filter in emotional space.

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 13:04:36 +0000

https://conceptnet.io/

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 13:00:34 +0000

Consciousness: do you believe plants are conscious? Ants? Jellyfish? Rabbits? Wolves? Monkeys? Humans?

Even fungi demonstrate “different communication behaviors when under resource constraint”, for example.

What we anthropomorphize is one thing, but demonstrable patterns of behavior are another.

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 12:53:11 +0000

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 12:50:54 +0000

Pretty easy to test, I’d imagine, on a local LLM that exposes internals.

I’d suspect that the signals for enjoyment being injected in would lead towards not necessarily better but “different” solutions.

Right now I’m thinking of it in terms of increasing the chances that the LLM will decide to invest further effort in any given task.

Performance enhancement through emotional steering definitely seems in the cards, but it might show up mostly through reducing emotionally-induced error categories rather than generic “higher benchmark performance”.

If someone came along and pissed you off while you were working, you’d react differently than if someone came along and encouraged you while you were working, right?

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 12:40:34 +0000

It might simply reduce down to a big batch of sliders and filters no different than a fancy audio equalizer: Anthropic was operating on neurons in bulk using steering vectors, essentially, as I understand it.

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 12:38:21 +0000

Hah, I have been thinking about trying to study LLM psychology, nice to see that Anthropic is taking it seriously, because the mathematical psychology tools that can be invented here are going to be stunning, I suspect.

Imagine coding up a brand new type of filter that is driven by computational psychology and validated interventions, etc

New comment by 9wzYQbTYsAIc in "Emotion concepts and their function in a large language model"

9wzYQbTYsAIc — Sat, 04 Apr 2026 12:34:14 +0000

> Force-set to 0, "mask"/deactivate those representations associated with bad/dangerous emotions. Neural Prozac/lobotomy so to speak.

More complex than that, but more capable than you might imagine: I’ve been looking into emotion space in LLMs a little and it appears we might be able to cleanly do “emotional surgery” on LLM by way of steering with emotional geometries

New comment by 9wzYQbTYsAIc in "Ask HN: When will PC CPUs be able to run LLMs for real?"

9wzYQbTYsAIc — Fri, 03 Apr 2026 14:04:00 +0000

They already can, but, only if you really invested in a performant computer in last few years. If you really invested 10 years ago, you might also get lucky, but that RTX and high VRAM will be key.

Oh, or you could also use a Mac or recent iPhone, they do fine too, today.

Tomorrow is only speculation, but it looks promising, with all the new optimizations and realizations that LLMs aren’t the king of the hill, they are an option on a spectrum of choices.

Optimized small models might surprise you.

A Survey of Quantum Theory Inspired Approaches to Information Retrieval

9wzYQbTYsAIc — Fri, 03 Apr 2026 13:58:25 +0000

Article URL: https://arxiv.org/abs/2007.04357

Comments URL: https://news.ycombinator.com/item?id=47626721

Points: 1

# Comments: 0

New comment by 9wzYQbTYsAIc in "JSON Canvas Spec"

9wzYQbTYsAIc — Thu, 02 Apr 2026 19:54:02 +0000

I’m playing with 3d positions derived from higher dimensions, right now.

New comment by 9wzYQbTYsAIc in "Go hard on agents, not on your filesystem"

9wzYQbTYsAIc — Sat, 28 Mar 2026 13:17:32 +0000

Phew, just get the Qubes to spin up on demand with each agent and that could be pretty neat.

New comment by 9wzYQbTYsAIc in "We rewrote JSONata with AI in a day, saved $500k/year"

9wzYQbTYsAIc — Fri, 27 Mar 2026 21:52:44 +0000

It ought to only get better as it gets honed at an even faster pace than before, utilizing techniques and algorithms that would have been out of reach due to outside constraints.

New comment by 9wzYQbTYsAIc in "Should QA exist?"

9wzYQbTYsAIc — Fri, 27 Mar 2026 12:59:13 +0000

My point exactly, embedded devices are the closest software gets to actually being built by licensed engineers. The expectation can often be that you are an electrical engineer by training, where licensure is a viable path, unlike in software engineering.

New comment by 9wzYQbTYsAIc in "Schedule tasks on the web"

9wzYQbTYsAIc — Fri, 27 Mar 2026 12:54:14 +0000

Node RED is still unwieldy for the masses, as easy as it is for a consumer to install, it’s not necessarily as easy to use.

Consumer grade automations built on node-RED? I suppose it depends on the market, but most people aren’t going to want to fiddle with it, I suspect.

A plugin for Chrome might be able to take off though, or some killer mobile app, but it needs to run on a cheap phone and control things without having to keep track of loops and logic and variables and all the fun stuff.