Hacker News: adw

New comment by adw in "We let AIs run radio stations"

adw — Tue, 19 May 2026 03:15:42 +0000

kexp.org in Seattle and San Francisco for a start.

New comment by adw in "The sigmoids won't save you"

adw — Fri, 15 May 2026 17:30:05 +0000

https://podcasts.apple.com/us/podcast/machine-learning-stree... is a pretty good primer on METR, what it measures, and its limitations.

New comment by adw in "New arXiv policy: 1-year ban for hallucinated references"

adw — Fri, 15 May 2026 02:55:01 +0000

arXiV is not intended to be your blog. You should be held to a zero-mistake standard when publishing academic work.

The people I worry for are the junior researchers who are going to be splash damage for dishonest PIs. The PIs, though, deserve everything that’s coming for them.

New comment by adw in "Google Flow Music"

adw — Sat, 25 Apr 2026 14:51:21 +0000

You are forgetting the albums KG and LW which are both microtonal. I knew exactly what you were saying :-)

New comment by adw in "Do I belong in tech anymore?"

adw — Sat, 25 Apr 2026 05:59:17 +0000

You’ve got nine years of experience, so work your network and get referrals. It’s very hard to get mid-career jobs through the front door; most people want someone they trust to vouch for you.

New comment by adw in "Google Flow Music"

adw — Sat, 25 Apr 2026 05:29:38 +0000

Bunch of Balkan and Turkish music has quarter tones too. (And you’re forgetting KG and LW…)

New comment by adw in "Coq theorem prover is now called Rocq"

adw — Sun, 19 Apr 2026 22:31:19 +0000

He did a stupid thing. Doesn’t make him stupid, but the action is. (Also this is a stock phrase.)

New comment by adw in "Changes in the system prompt between Claude Opus 4.6 and 4.7"

adw — Sun, 19 Apr 2026 22:30:39 +0000

When you’re staffing work to a junior, though, often it’s the opposite.

New comment by adw in "Coq theorem prover is now called Rocq"

adw — Sat, 18 Apr 2026 01:14:56 +0000

The author knew fine that it was a knob joke (https://news.ycombinator.com/item?id=26743882). In this specific case, play stupid games, get stupid prizes; no-one is asking Le Coq Sportif to rebrand or your local bistro to stop serving coq au vin.

New comment by adw in "HyperAgents: Self-referential self-improving agents"

adw — Thu, 26 Mar 2026 19:24:16 +0000

Completely unrelated. Recursive Language Models are just "what if we replaced putting all the long text into the context window with a REPL which lets you read parts of the context through tool calls and launch partitioned subagents", ie divide-and-conquer applied to attention space.

New comment by adw in "End of "Chat Control": EU parliament stops mass surveillance"

adw — Thu, 26 Mar 2026 17:08:45 +0000

You’re painting an EPP/ECR initiative as left wing? That’s inconsistent with the facts.

New comment by adw in "Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised"

adw — Tue, 24 Mar 2026 15:09:48 +0000

> In one of my vibe coded personal projects (Python and Rust project) I'm actually getting rid of most dependencies and vibe coding replacements that do just what I need. I think that we'll see far fewer dependencies in future projects.

No free lunch. LLMs are capable of writing exploitable code and you don’t get notifications (in the eg Dependabot sense, though it has its own problems) without audits.

New comment by adw in "The bureaucracy blocking the chance at a cure"

adw — Mon, 16 Mar 2026 19:30:07 +0000

Because it's inordinately more expensive.

We're computer people, so we have a good analogy here; the COVID vaccine did speculative branch prediction. They basically operated _as if_ they would get approval at all stages where they could, parallelizing much more of the process at the cost of a _very_ expensive branch fail if something went wrong.

New comment by adw in "Ghostmd: Ghostty but for Markdown Notes"

adw — Sun, 08 Mar 2026 01:08:43 +0000

And Glow.

New comment by adw in "A standard protocol to handle and discard low-effort, AI-Generated pull requests"

adw — Fri, 06 Mar 2026 02:51:26 +0000

If you know what you're doing, you can achieve good results with more or less any tool, including a properly-wielded coding agent. The problem is people who _don't_ know what they're doing.

New comment by adw in "Global Intelligence Crisis"

adw — Mon, 23 Feb 2026 20:18:42 +0000

> Organizations don't restructure at the speed of a demo.

I imagine I'm not alone in having seen a _big_ secular shift in colleague behavior since Opus 4.5 came out. The organization will lag the behavior, but weird things are happening.

(I'm not speaking to the rest of your points; the crypto-bro stable coin bit was jarring for me too. Europe will just go onto Faster Payments, the US will eventually catch up with FedNow, you don't need crypto).

New comment by adw in "Ladybird adopts Rust, with help from AI"

adw — Mon, 23 Feb 2026 17:29:21 +0000

It’s a very good way of getting LLMs to work autonomously for a long time; give it a spec and a complete test suite, shut the door; and ask it to call you when all the tests pass.

New comment by adw in "Loops is a federated, open-source TikTok"

adw — Mon, 23 Feb 2026 00:29:13 +0000

Football and F1 have become more popular by being less performatively male. Drive to Survive is The Real Househusbands of Oxfordshire (and Monaco).

New comment by adw in "Hello Worg, the Org-Mode Community"

adw — Mon, 23 Feb 2026 00:26:45 +0000

For many software businesses, licensing is an issue. The spec is GFDL with GPL code samples, a non-cleanroom translation of the elisp parser would (likely) be GPL (or at least arguably enough so to keep lawyers busy), so going and doing some other roughly equivalent markup language instead avoids the copyleft requirements.

So, yes, “too much trouble”, much of it nontechnical.

New comment by adw in "Ministry of Justice orders deletion of the UK's largest court reporting database"

adw — Mon, 16 Feb 2026 18:12:55 +0000

In the UK the equivalent is a DBS (Disclosure and Barring Service) check.