Hacker News: stbenjam

New comment by stbenjam in "C*: Unifying Programming and Verification in C"

stbenjam — Tue, 08 Sep 2026 18:40:09 +0000

By that logic, I think I'll create a new language called Pascal, or maybe Ada...

Show HN: Skillsaw – Linter for Context

stbenjam — Tue, 08 Sep 2026 17:35:46 +0000

Skillsaw started as claudelint and has grown to cover most ecosystems. It lints the contextual building blocks in a repository — skills, instructions, plugins, hooks, and tool configuration. It checks both structural correctness and content quality.

Comments URL: https://news.ycombinator.com/item?id=49613638

Points: 1

# Comments: 0

Are we measuring AI coding ability wrong?

stbenjam — Fri, 04 Sep 2026 11:46:32 +0000

Article URL: https://bitbin.de/qualitative-benchmarks/

Comments URL: https://news.ycombinator.com/item?id=49563287

Points: 1

# Comments: 0

New comment by stbenjam in "OpenClaw 2.0, Accidentally"

stbenjam — Mon, 31 Aug 2026 13:04:41 +0000

The risk here is wildly overstated, prompt injection risk is becoming vanishingly small with the latest frontier models.

I would not run an OpenClaw with full access to my bitwarden, but it certainly has some logins available to it, and can make purchases with link-cli which has human-in-the-loop.

New comment by stbenjam in "I spent $266 and four AI models to own my tablet. GLM-5.3 finished it in a day"

stbenjam — Sun, 30 Aug 2026 22:27:52 +0000

Ah sorry, for OpenAI it does seem automatic with ID verification. Anthropic's seems more picky.

New comment by stbenjam in "I spent $266 and four AI models to own my tablet. GLM-5.3 finished it in a day"

stbenjam — Sun, 23 Aug 2026 17:23:04 +0000

Apply, not sign up. It is not automatic and most will be refused.

New comment by stbenjam in "Managing AI Coding Costs at Scale"

stbenjam — Fri, 07 Aug 2026 22:34:50 +0000

$80 sounds extremely low for what you're describing - are you on API token plans?

I have had some $3,000 token days - even without Fable. I don't see how this is sustainable.

My personal 20x plans get so much usage for so cheap. The consumer subsidies are crazy, but alas I can't use them for work.

New comment by stbenjam in "Pi's Minimalism Is Its Advantage"

stbenjam — Wed, 05 Aug 2026 09:55:14 +0000

Pi is ok, but I dislike needing plugins to do anything useful. Subagents, MCP, /goal ... none of these things should be plugins.

New comment by stbenjam in "Patreon laying off 20% of staff"

stbenjam — Tue, 28 Jul 2026 11:10:34 +0000

My comment about legal reasons was legal reasons surrounding employee law suits from being laid off. At will employment in most US states allow you to state no reason, that's safer than offering any reason at all. A specific reason for a layoff can be litigated.

New comment by stbenjam in "Benchmarking Opus 5 on SlopCodeBench"

stbenjam — Tue, 28 Jul 2026 09:58:59 +0000

> I hope the big labs will start using this benchmark in their RL pipelines.

Labs do not train on benchmark data (allegedly). They can train on similar problems, but benchmarks have specific strings in them that labs are supposed to be aggressive in filtering out of their training corpora.

New comment by stbenjam in "Patreon laying off 20% of staff"

stbenjam — Fri, 24 Jul 2026 13:33:07 +0000

I assume it is legal reasons.

New comment by stbenjam in "TFTP Honey Pot Results"

stbenjam — Mon, 13 Jul 2026 20:43:18 +0000

I know tftp is still in wide use, I wonder if there's things out there looking for stuff that's less common like NNTP, finger servers, etc

New comment by stbenjam in "How to read more books"

stbenjam — Sun, 12 Jul 2026 18:03:49 +0000

Oh I didn't hear about this. That sucks. The stock firmware is terrible. CrossPoint makes it usable.

New comment by stbenjam in "How to read more books"

stbenjam — Sun, 12 Jul 2026 17:44:44 +0000

I adore my XTEink 4 with the crosspoint firmware. Best small form factor ereader

New comment by stbenjam in "Grok 4.5"

stbenjam — Thu, 09 Jul 2026 00:04:44 +0000

Elon's rhetoric doesn't really match the model's behavior. It is willing to criticize Elon and argues against many of the insane right way points he tries to make.

New comment by stbenjam in "Zuckerberg says AI agent development going slower than expected"

stbenjam — Sun, 05 Jul 2026 18:14:45 +0000

The gulf is bridgeable. The problem is that a lot of people are building agents without strong enough judgment layers around them. Work that can be verified with reasonable accuracy are the sweet spot right now.

New comment by stbenjam in "HPV vaccine cuts risk of dying from cervical cancer before 30"

stbenjam — Mon, 29 Jun 2026 13:50:49 +0000

No need to be defensive. If you ask an epidemiologist, they would almost certainly agree that it is essentially a marker of sexual activity at this point. It is transmissible even with condoms, it has many strains, it is widely prevalent, and the WHO states that basically everyone is sexual active will get one strain. Guardrail prevents against 9 - the ones we were able to create vaccines for and we know have negative effects.

There's also not really great tests for it, so you do not know if you have it or not.

New comment by stbenjam in "We all depend on open source. We will defend it together"

stbenjam — Mon, 29 Jun 2026 13:46:39 +0000

I guess you'd rather downvote than answer the question.

New comment by stbenjam in "GLM 5.2 beats Claude in our benchmarks"

stbenjam — Mon, 29 Jun 2026 13:45:52 +0000

Chinese models are almost certainly cheating on benchmarks, I would bet if you saw the training data that the benchmark canaries are in there.

GLM may be a good model in general but it s benchmaxxed and definitely not as good as Opus 4.8.

New comment by stbenjam in "We all depend on open source. We will defend it together"

stbenjam — Fri, 26 Jun 2026 12:24:09 +0000

You realize that the companies listed employ many of the core open source maintainers for large projects? It is project-specific, but 80% of Linux kernel development is from paid corporate employees. Similar for kubernetes. All the load bearing infrastructure is already handled by these companies... literally no one else is going to have the resources or experience to redirect large efforts on securing F/OSS.

What would you propose otherwise?