Hacker News: petercooper

New comment by petercooper in "Ask HN: What do you run on a $5 VPS that's worth keeping online 24/7?"

petercooper — Fri, 09 Oct 2026 08:53:22 +0000

A bit frivolous, but I once used a spare VPS like that as a one-listener Internet radio station for my mom which worked with her portable radio (she has no interest in using Spotify etc.)

New comment by petercooper in "Clef: Open-weight decision models, and new RL fine-tuning platform"

petercooper — Thu, 01 Oct 2026 16:45:26 +0000

Smaller models have been able to do these sorts of tasks, but a little slower, for a while now. Give a small Qwen 3.8 model a classification task and force a structured output, and it'll do a good job. I've used Qwen 0.8b for basic image classification in <500ms on my local machine for a while now.

There are a few technical details that can reduce the latency significantly (covered in the post) but the real insight has been from watching the reaction to Jev and seeing that there's enough of a market interest to offer it as a distinct thing. The underlying concept/approach was already there.

New comment by petercooper in "Jev in 25 Lines of Python"

petercooper — Wed, 23 Sep 2026 09:32:48 +0000

You can also go beyond Jev. Qwen 3.5 0.8B is fantastic at basic image classification/question answering (including OCR elements) also. Though rather than looking at logits, I get it to output a structured JSON object and it does simple object classification tasks on a Mac at under 500ms a pop (I forget how far, but I think it's like ~250ms) with good accuracy (depending on task).

New comment by petercooper in "People hooked on vapes try a new way to quit: cigarettes"

petercooper — Wed, 23 Sep 2026 08:17:08 +0000

I've had similar thoughts! I grew up around a heavy smoker. My dad told me to never smoke and I never have. But I randomly tried a nicotine lozenge in my 40s and found it such a "lightbulb on" moment that I've been using pouches for a few years now and my executive functioning still feels better for it (though not as much now as in the first two years, alas).

New comment by petercooper in "I said no and Apple said yes"

petercooper — Tue, 22 Sep 2026 10:20:50 +0000

I had a similar thing with Xcode the other day. I unticked the "download a code assistance model" thing, clicked to continue and it started downloading it anyway (which, to be fair, you can just X out of).

New comment by petercooper in "I turned Jev into a (lousy) chatbot"

petercooper — Mon, 21 Sep 2026 12:13:46 +0000

There might be some practical applications of this sort of idea like in situations where you want/have a heavily restricted vocabulary to build from. You can already do this with LLMs but they can get very... "distressed" if you force logits, whereas this would not.

Come to think of it, I'm now curious if it would do well at building SQL queries, say. (30 minutes later: I tried it, and it can do it reasonably well, but a normal model and linting will outperform it, though the inherent guard rails of a limited vocab are still intriguing.)

New comment by petercooper in "Flights cancelled at UK airports due to ATC issue"

petercooper — Tue, 08 Sep 2026 20:42:24 +0000

I believe the compensation part only kicks in if it’s the airline’s fault.

Language-agnostic WebGPU syntax highlighter

petercooper — Tue, 08 Sep 2026 17:10:22 +0000

Article URL: https://gpu-lexer.vercel.app/

Comments URL: https://news.ycombinator.com/item?id=49613220

Points: 2

# Comments: 0

New comment by petercooper in "Show HN: Restoredrill – proves your Postgres backups restore"

petercooper — Sat, 29 Aug 2026 14:50:35 +0000

CLaude, in particular, quietly, but genuinely and deliberately, overuses adverbs.

New comment by petercooper in "Run Qwen3.8 27B locally: real numbers from my Mac Studio"

petercooper — Fri, 28 Aug 2026 18:10:37 +0000

FWIW, on my Mac Studio I get ~24-27 tok/s generation between 0-16k context in - that's on the Q6_K GGUF with speculative decoding on. I have spent zero effort optimizing/improving this so far but will be trying the 4 bit MLX next (I've tended to find models drop off somewhat below 6 bit but maybe that isn't the case nowadays).

New comment by petercooper in "New Mac Studio with M5 Max and M5 Ultra"

petercooper — Tue, 25 Aug 2026 13:33:40 +0000

How's the compute side now, I wonder? Because while the Ultras have impressive memory bandwidth for inference, processing prompts still takes a dog's age on my M3 Ultra. I heard the M5 makes some strides forward in this area, though, and the M7 in particular promises to go a lot further.

New comment by petercooper in "New Mac Studio with M5 Max and M5 Ultra"

petercooper — Tue, 25 Aug 2026 13:31:57 +0000

More likely double that, even. I think you'd still see many buyers there. You can spend like $16k alone on a RTX 6000 PRO with a mere 96GB of VRAM now..

New comment by petercooper in "New Mac Studio with M5 Max and M5 Ultra"

petercooper — Tue, 25 Aug 2026 13:28:39 +0000

They seem to be suffering from the supply constraints like everyone else. They phased out the higher capacities on the M3 Ultra Mac Studio a while ago, and if you order a 128GB MBP, say, you're looking at six weeks or more for delivery.

New comment by petercooper in "New Mac Studio with M5 Max and M5 Ultra"

petercooper — Tue, 25 Aug 2026 13:25:48 +0000

Allegedly, they aren't making a big deal out of the M6 which won't have Pro, Max or Ultra configs at all, instead waiting for the M7: https://9to5mac.com/2026/08/08/apple-m7-chip-heres-why-it-ma...

New comment by petercooper in "OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)"

petercooper — Mon, 24 Aug 2026 17:16:04 +0000

It reminds me conceptually of the idea of using a ST:TNG replicator to just give you another replicator of your own, or asking a stereotypical genie for "infinite wishes". The genie is indeed out of the bottle in many ways.

New comment by petercooper in "DeepSeek API Pricing Update"

petercooper — Thu, 13 Aug 2026 14:01:42 +0000

As well as the headline in/out changes, people heavily using agentic coding tools will want to note the 6x (off peak) and 12x (peak) increase to cache hit pricing on Pro (since cache hit can easily make up 90%+ of input on long sessions).

DeepSeek was hugely underpricing cache hit pricing before and even after this increase they're still cheaper on that metric than every other provider I'm aware of, but it will put an end to those "I used 1 billion tokens and spent $4" reports.

New comment by petercooper in "DeepSeek planning to significantly raise prices"

petercooper — Thu, 13 Aug 2026 12:04:35 +0000

And confirmed: https://x.com/deepseek_ai/status/2087864589895798968

Pro's cache hit prices are 12x or 6x higher now depending on time of day.

New comment by petercooper in "DeepSeek V4 Pro 0813 quietly released"

petercooper — Wed, 12 Aug 2026 17:26:18 +0000

"quietly" is the biggest AI writing tell of Q3 2026.

New comment by petercooper in "The brain may be about to have its Ozempic moment"

petercooper — Tue, 11 Aug 2026 20:48:22 +0000

Not to take away from the broader point, but modafinil is lumped in with methylphenidate as a stimulant that "increase[s] the activity of neurotransmitters such as dopamine and norepinephrine". Modafinil does also stimulate the orexin system and is part of why it's so effective for wakefulness and not as a stimulant in the medium/long-term.

New comment by petercooper in "Taxi drivers rarely die of Alzheimer's"

petercooper — Sun, 09 Aug 2026 22:53:52 +0000

No, it’s a licensed black cab thing. London has had mini cabs as well for many decades who didn’t need to study anything and were not even licensed till about 20 years ago. However, their downside is they have to be prebooked and can not be hailed on the street. Apps count as booking and not hailing I guess.