Hacker News: regularfry

New comment by regularfry in "DeepSeek-V4-Flash Update"

regularfry — Fri, 31 Jul 2026 08:02:18 +0000

It's good but (at least on openrouter) it's got an annoyingly tight output token limit. So if it does get stuck in a reasoning pit, it won't work its way out of it in time.

It's replaced the Kimi models for me though.

New comment by regularfry in "Some thoughts about Anthropic's new cryptanalysis results"

regularfry — Thu, 30 Jul 2026 08:23:45 +0000

For me it's more an expression of how much mileage you can get out of "glorified", how many tasks devolve down to "if you model language accurately enough, look what drops out" because it turns out that to model language you need to model how the world works. I don't use it to minimise the capabilities at all.

New comment by regularfry in "Some thoughts about Anthropic's new cryptanalysis results"

regularfry — Thu, 30 Jul 2026 08:20:49 +0000

The wikipedia definition is:

> ...a hypothetical type of artificial intelligence that matches or surpasses human capabilities across virtually all cognitive tasks.

You can argue that paperclip maximising is an inevitable consequence of that (and the huggingface breach is interesting from that point of view) but it's not fundamental to the definition.

The question then is what "surpasses human capabilities" means and we're there in some niches but not all, and not across many models.

New comment by regularfry in "Keychron announces first open-source firmware for gaming mice"

regularfry — Thu, 30 Jul 2026 08:13:20 +0000

I've just grabbed myself a Nape Pro trackball. It's really quite neat. ZMK firmware (which was actually the main thing I wanted) and a configurable positioning angle. I'm still getting used to it but so far it looks like a decent addition to my wireless toolkit.

I would prefer a bigger trackball as a daily driver, but it's an interesting device otherwise. It feels like they could reasonably do a mini version, too, just by chopping the non-main buttons in half. Definitely going to crack it open and see what the innards look like.

New comment by regularfry in "Handbook.md shows that long policy documents do not reliably govern agents"

regularfry — Wed, 29 Jul 2026 16:23:25 +0000

Control vectors for the win? It feels like the way to fix this is to pull out a control vector immediately after processing the handbook and use that to steer later inference. That should stop the drift over long distances, but it doesn't guard against the handbook itself being too big.

New comment by regularfry in "Show HN: Formally verified 3D CSG: Trust 93 lines spec, not 1000 lines AI code"

regularfry — Tue, 28 Jul 2026 15:43:55 +0000

CSG on meshes isn't really where FreeCAD struggles or focuses. That's more BRep, which is a harder problem than CSG.

Blender used to struggle with boolean operations, though. Seems to have got much better some time in the last couple of years, but without knowing any of the backstory I don't know if they've bodged it into shape or would benefit from something proven.

New comment by regularfry in "Vehicle Motion Cues"

regularfry — Tue, 28 Jul 2026 11:57:51 +0000

When did you try it? I got a bit confused by your comment because there's no obvious reason why the accelerometers in an android phone would have a problem reporting forward/backward acceleration any less accurately than lateral. So I installed it and the 'Dots' mode definitely responds to acceleration normal to the screen, but that mode is marked as 'New' so might not have been present when you last looked.

New comment by regularfry in "What Even Are Microservices?"

regularfry — Tue, 28 Jul 2026 11:29:07 +0000

If you're needing to share code for domain objects between microservices something has gone badly wrong.

New comment by regularfry in "What Even Are Microservices?"

regularfry — Tue, 28 Jul 2026 11:27:58 +0000

The very first time I came across the term, it was used to refer to something so small that you'd comfortably rewrite it rather than fix it if it was wrong.

New comment by regularfry in "What Even Are Microservices?"

regularfry — Tue, 28 Jul 2026 11:23:52 +0000

It's not just the modular organisation that you've got to get right though, although that's definitely a big thing. Deployment independence matters too: if I've got a perfectly modular monolith but I have to coordinate with everyone else who lives in that monolith to get my module into production, it's leaving half the gains on the table.

New comment by regularfry in "What Even Are Microservices?"

regularfry — Tue, 28 Jul 2026 11:19:12 +0000

One team owning many services is fine, as long as they can deploy them independently of any other team. Less critical (but still useful) is being able to deploy their own services independently of each other.

New comment by regularfry in "Claude Opus 5"

regularfry — Sat, 25 Jul 2026 09:16:59 +0000

This isn't mimicking what a human would do, because it is an exceedingly rare human who would write their own renderer for a task needing a CAD file generating. The human who is capable of doing both is rare, let alone the human who can do it in any sort of reasonable time. Saying "but it's in the training data" is a cop-out: it's in Google too, would I do it? No. I would not.

New comment by regularfry in "Why Software Factories Fail (or: harness engineering is not enough)"

regularfry — Fri, 24 Jul 2026 07:17:01 +0000

The whole point is that if you don't maintain high quality, any software will degrade to the point where the factory breaks. "Human-quality" here isn't quite the right measure because human software factories also bog down in exactly this way.

New comment by regularfry in "Laguna S 2.1"

regularfry — Wed, 22 Jul 2026 17:06:47 +0000

I got usable token rates (10-20tps from memory, so marginal) with the Qwen A10B a while back, well before all the new speculative speedups landed in llama.cpp. There's an unmerged branch which allegedly supports this, but I don't know how well yet. Looks worth investigating but I might give it a few days to see what bugs get shaken loose.

New comment by regularfry in "Laguna S 2.1"

regularfry — Wed, 22 Jul 2026 12:01:13 +0000

What's your hardware? I've got 64GB RAM and a 4090 here, wondering if it's worth a play.

New comment by regularfry in "Gemini last models: temperature, top_p, and top_k are deprecated and ignored"

regularfry — Wed, 22 Jul 2026 11:52:05 +0000

Couple of other more businessy reasons:

- SynthID hides the watermark in the sampling RNG. No randomness -> no watermark.

- If you want to distil on the model outputs, you want temp=0 outputs. No temp=0 -> worse distillation.

New comment by regularfry in "The drivers behind software delivery inefficiency"

regularfry — Wed, 22 Jul 2026 08:14:21 +0000

The team. The organisation. The reviewer, if they care about team throughput.

New comment by regularfry in "The drivers behind software delivery inefficiency"

regularfry — Tue, 21 Jul 2026 08:56:44 +0000

That is the context switch I'm referring to. It's worth the reviewer suffering a 15 minute (say) flow state loss to avoid the multiple hours the ticket would otherwise have been waiting to be picked up.

New comment by regularfry in "The drivers behind software delivery inefficiency"

regularfry — Mon, 20 Jul 2026 22:49:20 +0000

For us, review latency was obviously a problem so we eliminated it (for most tickets, anyway) by making the handover synchronous. Get on a call with the reviewer when it goes into the review column. The win from eliminating review latency massively outweighs the context switch cost for the reviewer. All the more so when the patch is small enough to actually read through on the call, so if there is anything immediate to address you can ping-pong it without anything waiting.

New comment by regularfry in "Claude Fable produced a counterexample to the Jacobian Conjecture"

regularfry — Mon, 20 Jul 2026 11:58:03 +0000

The reasoning trace would be far more interesting, and that's not exposed.