Hacker News Reader

roywigginson Microsoft killed FoxPro in 2007. Anyway, here's FoxPro revived

Right, yes, this sort of style certainly can be produced by writers, especially ones who are working in a particular corporate universe. That's where LLMs got it from! It just sucks that everyone "writes" like that now. Every new one-person project or company is incongruously spouting corporatese. Don't we get enough of that already? Flattening everything into American corpo-speak sucks.

roywigginson Microsoft killed FoxPro in 2007. Anyway, here's FoxPro revived

The website is obviously and gratingly LLM-voiced. I don't know how people aren't tired of paragraphs like this yet:

"Visual FoxPro is a 32-bit program, and that decides more than it appears to. It is why a table stops at two gigabytes, why a memo file stops at two gigabytes, and why a big report runs out of memory on a machine with plenty to spare. The limits are signed 32-bit numbers buried in the file handling, not a licensing decision anybody made."

and

"The editor checks what you type through that very compiler, so what it underlines and what the runtime refuses cannot drift apart."

Like, what? Who talks like that?

roywigginson HarnessTax: How Much Does the Harness Matter for Coding Agents?

It's not hard to sandbox Pi without adding anything substantial to the actual size of the system prompt, which is what HarnessTax is mostly measuring. Wrapping it in nono.sh costs approximately zero tokens.

(I do think Pi should ship with more than zero builtin sandboxing though)

roywigginson HarnessTax: How Much Does the Harness Matter for Coding Agents?

I've found the experience of using Pi with local models feels a lot snappier than both OpenCode or Claude Code.

roywigginson Libraries Run Rust Inside Python (With PyO3)

For me, it's simply that I have to read Claudese instrumentally for work enough that I am not going to spend my neurons reading it idly. I am not mad about it or anything, it just sucks to open up a blog post and realize that it's just Claude again under a different name.

roywigginson Libraries Run Rust Inside Python (With PyO3)

> reach for, a Rust extension does the work

ai; dr, sorry

roywigginson LG denies TV spying claims, says tracking and snooping concerns 'not true'

No less than Shazam is?

roywigginson Europe's "Less" Is Doing More Than Anyone Gives It Credit For

Pangram flags it. It also talks about "quietly" and "the gap". It's AI.

roywigginson Europe's "Less" Is Doing More Than Anyone Gives It Credit For

ai; dr, sorry

roywigginson A misalignment of AI in mathematics

If there's a machine that automatically turns electricity into proofs then mathematics becomes a different thing altogether.

roywigginson Tao: Open math problems being non-renewably mined by AI

https://en.wikipedia.org/wiki/Decline_in_insect_populations

roywigginson Tao: Open math problems being non-renewably mined by AI

Today, maybe. Where's the law of nature that says it won't be generating novel insights in two years? Five? Ten?

roywigginson Tao: Open math problems being non-renewably mined by AI

If AI can generate questions and then answer them, what are the people for?

roywigginson Actively exploited sandbox RCE in all Chromium versions

> I chained this bug with an n-day sandbox escape and flagged the v8CTF.

https://serotav.github.io/Writeups/v8/when-sorting-leads-to-...

roywigginson Any Human Ever – One life, drawn at random from all who have ever lived

A similar site, also LLM-assisted, that does a better and more evocative job of composing stories.

https://random-lives.github.io/random-lives/

roywigginson How accurate have Ed Zitron's AI skeptic predictions been?

> The subsequent creation of bigger explosions by packing more fissile material does not meaningfully improve the technology.

That's not a great summary of what happened with the invention of the H-bomb.

roywigginson Claude Fable 5.1 and Claude Mythos 5.1

Fable zaps anything that seems even vaguely biological.

roywigginson How accurate have Ed Zitron's AI skeptic predictions been?

It seems to me that if they'd just about reached their upper limits in early 2024 agentic coding wouldn't be eating software development like it is now, and wasn't then.

roywigginson How accurate have Ed Zitron's AI skeptic predictions been?

> In the first case, TFA refutes by claiming 'wrong' repeatedly, which does not convince me of anything. If anything, Zitron is probably right in this regard, since the majority of progress in recent LLM tech has been setting up of guardrails to cajole the models using 'agents'.

I am certain that plugging a circa 2023 model into a 2026 harness would be a pretty frustrating experience. Yes, you could code a bit with AI in 2023, but models are just much better at it than they used to be. And smaller open models are leaps and bounds better at it than they were three years ago.

roywigginson Racter (1984)

Constructing the Other Half of The Policeman’s Beard (2021)

https://electronicbookreview.com/publications/constructing-t...

roywigginson C2PA Cameras Do Not Survive Contact with Reality

Transferring electronic images to film is a long-solved problem.

https://en.wikipedia.org/wiki/Film_recorder

roywigginson fx :Tiny, open, native coding agent.

Package managers constrain what software can do?

roywigginson fx :Tiny, open, native coding agent.

Not long. We are transitioning to your LLM curling an arbitrary markdown file and doing whatever it says.

roywigginson fx :Tiny, open, native coding agent.

It's a brand new type of software. Nobody knows what the best way to do it is so a lot of people are trying stuff out, and a lot of people are interested in new ideas.

roywigginson Anthropic's ‘watermark’ text adulteration in Claude is a perversion of writing

it serves to show just how little regard the people behind these generated-text fingerprinting schemes have for the actual craft of writing.

LLMs have never been the place I've thought to expect any commitment to the craft of writing, to be fair.

roywigginson DeepSeek Harness developer preview

Not without nuking your cache, I figure.

roywigginson Docker Sandboxes – Disposable, isolated sandboxes for AI agents

Only if the replacement is global and not, say, only looking and inserting it into the actual (eg) Authorization header. If something is only transparently altering the Authorization header, then an agent inserting the dummy value somewhere else is totally safe.

roywigginson How I use LLMs to learn complex topics

It has a sort of metronomic quality. It never slows down or speeds up or modulates its tone. It plods forward at a relentless pace and never has a light touch with anything.

I think this is one reason why LLM text is pretty exhausting to read for long stretches.

roywigginson Humans missed 1 in 3 threats approving AI agent commands across 40k game runs

I guess ideally you'd want to force it to pipe each step back into the agent/IDE for display (and optionally wait for approval) rather than shoving it into the context. And with some sort of heuristic to skip commands that are piped into sed and similar.

or use just use actual files instead of pipes with a permissions dialogue gate on write. That would work already in Claude I think, and with IDE integration it would show each step as it went.

Of course buffering every step of a pipeline will have its own side-effects.

roywigginson I am retiring from fulltime writing (& pseudonymity) to launch Guardian Angel

Claude had some pretty good ideas about how to end the war in Iran when I asked it a while ago (The US should sue for peace, I believe was the conclusion).