Hacker News: ppeetteerr

New comment by ppeetteerr in "1-Bit Bonsai Image 4B Image Generation for Local Devices"

ppeetteerr — Mon, 01 Jun 2026 04:00:11 +0000

Yes, size and performance are not only problems for local LLMs, they are problems for frontier LLM companies like OpenAI and Anthropic. The latter still lose a ton of money on inference and advances in efficient, performant models helps their bottom line.

New comment by ppeetteerr in "Evals will break"

ppeetteerr — Fri, 22 May 2026 04:51:03 +0000

They are addressed but the core of the thesis is still wrong:

> This is the core problem: our entire evaluation infrastructure is structurally reactive. We measure the system after it has changed. We never predict the change.

That's kind of the point of evals.

New comment by ppeetteerr in "Evals will break"

ppeetteerr — Wed, 20 May 2026 05:52:54 +0000

The argument in the article is backwards. Evals test the stability and boundaries of a concept. They are not created before the concept has been prototyped (which the author acknowledges).

An eval is not somehow breaking silently due to some new capabilities in an LLM. It wouldn't be a good eval if it did. What it does is steer the LLM towards specific goals. If anything, an argument can be made that they restrict creativity and experimentation by narrowing goals.

If the argument is that evals need to written before some new behavior can be devised, that's incorrect. There are an infinite number of evals that test for things which cannot be done. Only when something has been demonstrated to work in a specific context, can an eval be written.

New comment by ppeetteerr in "Show HN: Broccoli, one shot coding agent on the cloud"

ppeetteerr — Wed, 22 Apr 2026 20:00:43 +0000

How does this compare to using Claude Web with connectors to build the same feature?

On a separate note, READMEs written by AI are unpleasant to read. It would be great if they were written by a human for humans.

New comment by ppeetteerr in "EFF is leaving X"

ppeetteerr — Thu, 09 Apr 2026 18:19:15 +0000

I applaud the move. It's also a little disingenuous to talk about moral standings when the third opening sentence is "The math hasn’t worked out for a while now." If the numbers were working out, would they continue to turn a blind eye on the privacy tracking?

New comment by ppeetteerr in "A sufficiently detailed spec is code"

ppeetteerr — Thu, 19 Mar 2026 17:19:47 +0000

Too much of code is data transformation. input -> sanitation -> db -> consumer -> api -> client. Business logic defines the shape of that data and some service-level rules but the majority is just shoveling data.

New comment by ppeetteerr in "Tech employment now significantly worse than the 2008 or 2020 recessions"

ppeetteerr — Fri, 06 Mar 2026 18:37:13 +0000

Those are raw numbers. I would look instead at the job changes over total employment numbers. I don't have the numbers but I would wager we have many more people working in tech today (overall) than we did in 2008.

Also, that spike in 21/22 really did a number on people's expectations. The one constant in this industry is its cyclical nature.

New comment by ppeetteerr in "MacBook Neo"

ppeetteerr — Thu, 05 Mar 2026 23:20:08 +0000

Used, yeah

New comment by ppeetteerr in "MacBook Neo"

ppeetteerr — Wed, 04 Mar 2026 20:08:22 +0000

This laptop competes against M2/M3 MacBook Airs. Going to be hard to justify a Neo when the others are so much more powerful.

New comment by ppeetteerr in "Layoffs at Block"

ppeetteerr — Thu, 26 Feb 2026 22:33:30 +0000

Wishing the best for all those affected and excited to see many of you start new companies and continue to innovate.

New comment by ppeetteerr in "The political effects of X's feed algorithm"

ppeetteerr — Wed, 18 Feb 2026 20:50:56 +0000

Why anyone is still using X after 2025 is a mystery (I know, it's where everyone is, but the moral implications are wild)

New comment by ppeetteerr in "A new bill in New York would require disclaimers on AI-generated news content"

ppeetteerr — Fri, 06 Feb 2026 18:15:28 +0000

Publishing is more than just authoring. You have research, drafts, edits, source verification, voice, formatting, multiple edits for different platforms and mediums. Each one of those steps could be done by AI. It's not a single-shot process.

New comment by ppeetteerr in "Data centers in space makes no sense"

ppeetteerr — Wed, 04 Feb 2026 00:39:59 +0000

Don't let common sense stop you from a good time.

New comment by ppeetteerr in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

ppeetteerr — Sat, 31 Jan 2026 05:33:18 +0000

We’re about to see if LLM regress or evolve

New comment by ppeetteerr in "Velox: A Port of Tauri to Swift by Miguel de Icaza"

ppeetteerr — Tue, 27 Jan 2026 15:07:58 +0000

That's right, I said TypeScript but yeah, it's v8 under the hood.

New comment by ppeetteerr in "Velox: A Port of Tauri to Swift by Miguel de Icaza"

ppeetteerr — Tue, 27 Jan 2026 14:21:02 +0000

Not quite systems programming but this might give you some insight. Swift is memory efficient, and runs stable backend services. I've seen benchmarks showing that it's slightly more performant than typescript but twice as memory efficient (but not as efficient when it comes to memory management compared to Rust, C, and C++).

The other point I've seen is that its string library is slow and very accurate.

Besides that, the C-interop means you have quite a bit of flexibility in leveraging existing libraries.

New comment by ppeetteerr in "Unrolling the Codex agent loop"

ppeetteerr — Fri, 23 Jan 2026 22:00:21 +0000

Nothing particularly insightful other than avoiding messing with previous messages so as not to mess with the cache.

New comment by ppeetteerr in "Unrolling the Codex agent loop"

ppeetteerr — Fri, 23 Jan 2026 21:57:10 +0000

I asked Claude to summarize the article and it was blocked haha. Fortunately, I have the Claude plugin in chrome installed and it used the plugin to read the contents of the page.

New comment by ppeetteerr in "Ask HN: How can we solve the loneliness epidemic?"

ppeetteerr — Thu, 22 Jan 2026 16:32:19 +0000

Before people in this country can unionize, they have to see their peers and fellows, not as strangers. The structures in this country have put each person against the other in pursuit of wealth.

New comment by ppeetteerr in "Skip is now free and open source"

ppeetteerr — Wed, 21 Jan 2026 23:57:31 +0000

Engineers are happy to pay for tools (hello, Claude Code). Libraries are quite different and it's a little uncomfortable to build a business on a closed-source, proprietary library.