Hacker News: Smaug123

New comment by Smaug123 in "The gap between open weights LLMs and closed source LLMs"

Smaug123 — Fri, 26 Jun 2026 22:15:34 +0000

The model itself, sure; the comment is about the production of more advanced models (to keep open weights near the frontier).

New comment by Smaug123 in "OpenAI unveils its first custom chip, built by Broadcom"

Smaug123 — Wed, 24 Jun 2026 20:21:53 +0000

By the way, you've seen Cerebras? It's not gone as far as what you described - loads of cores and RAM but you still load up the weights onto it as software and they need to be streamed into the chip for large models - but it is a whole wafer.

New comment by Smaug123 in "Correlated randomness in Slay the Spire 2"

Smaug123 — Tue, 16 Jun 2026 14:48:43 +0000

For what it’s worth, Claude did this without even being asked when I had it implement /dev/urandom in my deterministic dotnet runtime. (Fun fact: if the runtime only ever receives zero bytes from /dev/urandom then it will hang on attempting to initialise System.Random! That was the first way I asked for it to be implemented.)

New comment by Smaug123 in "Are you expected to run five Python type-checkers now?"

Smaug123 — Mon, 08 Jun 2026 21:56:05 +0000

Does it have a terse syntax? I main F#, and when I have to work with Python I generally find myself complaining about how verbose it is. (Needing intermediate variables for what should have been a pipeline, the ceremony around parallelism, having to store constructor parameters as object fields, etc.)

New comment by Smaug123 in "WoofWare.PawPrint, a Deterministic .NET Runtime"

Smaug123 — Sun, 07 Jun 2026 05:37:27 +0000

I didn't want to reimplement all the assembly-reading nonsense that comes for free with System.Reflection.Metadata. The `dotnetdll` crate exists but is GPL. Also in F# I can fall back to the CLR for fiddly things I don't want to implement (like the arithmetic opcodes on floats or whatever).

New comment by Smaug123 in "WoofWare.PawPrint, a Deterministic .NET Runtime"

Smaug123 — Sat, 06 Jun 2026 20:20:55 +0000

To answer your question, although I would certainly have preferred you to phrase your comments less insultingly: this project would otherwise never have got to a state where it could find bugs. I am not paid to write this code, and it would have taken far more years than I would have been willing to spend.

It's not actually unheard of for people to pay other entities to build their passion projects. For example, I visited [Eltham Palace](https://en.wikipedia.org/wiki/Eltham_Palace) last weekend, which was not in fact built entirely by the two Courthaulds who commissioned it.

New comment by Smaug123 in "WoofWare.PawPrint, a Deterministic .NET Runtime"

Smaug123 — Sat, 06 Jun 2026 20:12:27 +0000

I mean, there is a reason the MIT licence contains these words:

> THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND… INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF… FITNESS FOR A PARTICULAR PURPOSE…

If you would like a tool built with my organic artisanal human fingers, then I am certainly open to sufficiently large offers of money to build one for you! Alternatively, you can simply not use it if you think it won't fit your needs :)

New comment by Smaug123 in "Lockdown Mode"

Smaug123 — Sat, 06 Jun 2026 05:55:24 +0000

I think the Stroop effect ("read these colour names, each written in a different colour") is probably the purest demonstration of this. Humans are trivially prompt-injectable.

New comment by Smaug123 in "Ask HN: What was your "oh shit" moment with GenAI?"

Smaug123 — Fri, 05 Jun 2026 19:43:45 +0000

A few years ago, as you say, this was true. Nowadays I guess you just have to bite the bullet that Erdős problems aren’t interesting.

New comment by Smaug123 in "WoofWare.PawPrint, a Deterministic .NET Runtime"

Smaug123 — Thu, 04 Jun 2026 07:32:20 +0000

Something of a passion project. It's going to fail horribly if you try and use it, I'm sure, but it can already do some neat stuff!

WoofWare.PawPrint, a Deterministic .NET Runtime

Smaug123 — Thu, 04 Jun 2026 07:32:20 +0000

Article URL: https://www.patrickstevens.co.uk/posts/2026-06-04-announcing-woofware-pawprint/

Comments URL: https://news.ycombinator.com/item?id=48395370

Points: 59

# Comments: 18

New comment by Smaug123 in "ATLAS: Autoformalized Textbook Library At Scale"

Smaug123 — Fri, 29 May 2026 19:02:40 +0000

I take a very dim view of slopping out 500kloc and then giving it to unpaid experts to perform the actual work of checking it (confirmed at https://leanprover.zulipchat.com/#narrow/channel/583336-Auto... that this is what they did), especially given the reported incorrectness of the code (https://leanprover.zulipchat.com/#narrow/channel/583336-Auto... or https://leanprover.zulipchat.com/#narrow/channel/583336-Auto... for example).

They say in the Lean Zulip thread that this is actually intentionally a "low quality" release (https://leanprover.zulipchat.com/#narrow/channel/583336-Auto...); the paper notes that the quality is "inferior to that of expert-written Lean code". Then again, "Our results suggest that formalizing the core textbook infrastructure of modern mathematics is within reach".

New comment by Smaug123 in "Claude Opus 4.8"

Smaug123 — Thu, 28 May 2026 17:06:06 +0000

("If grown, then unpredictable" is unrelated to your apparent attempted refutation "But X is unpredictable and not grown; checkmate".)

New comment by Smaug123 in "Ask HN: Is anyone working at least 4 hours daily on an Apple Vision Pro?"

Smaug123 — Tue, 26 May 2026 06:25:07 +0000

I'm not, but is it yet possible to use the Vision Pro as a window manager for macOS? I'd totally get one if it were possible to lay out ordinary macOS windows in space rather than being confined to the simulation of a single rectangular screen.

New comment by Smaug123 in "Project Glasswing: An Initial Update"

Smaug123 — Sat, 23 May 2026 07:01:46 +0000

It’s still not clear to me that humanity was ready for GPT-2! Quite a lot of people claim to hate and fear LLMs. https://www.kcl.ac.uk/news/one-in-five-britons-think-ai-will... or https://yougov.com/en-us/articles/54762-most-americans-say-a... for example.

New comment by Smaug123 in "Project Glasswing: An Initial Update"

Smaug123 — Sat, 23 May 2026 06:52:17 +0000

By the way, you might be interested in looking up “blameless post-mortems” and indeed the field of incident response more generally. Modern incident response practice is to treat failures of an individual to do something as problems with the system they were operating in, because humans aren’t designed to be consistent or perfect and therefore shouldn’t be pretended or assumed to be.

New comment by Smaug123 in "Project Glasswing: An Initial Update"

Smaug123 — Fri, 22 May 2026 20:05:05 +0000

I think it's more that the requested information is prominently featured in the article, and indeed is the content of the only graphic in the article below the intro banner.

New comment by Smaug123 in "Project Glasswing: An Initial Update"

Smaug123 — Fri, 22 May 2026 19:53:44 +0000

> So far, Mythos Preview has found what it estimates are 6,202 high- or critical-severity vulnerabilities in these projects (out of 23,019 in total, including those it estimates as medium- or low-severity).

> 1,752 of those high- or critical-rated vulnerabilities have now been carefully assessed by one of six independent security research firms, or in a small number of cases by ourselves. Of these, 90.6% (1,587) have proved to be valid true positives, and 62.4% (1,094) were confirmed as either high- or critical-severity. That means that even if Mythos Preview finds no further vulnerabilities, at our current post-triage true-positive rates, it’s on track to have surfaced nearly 3,900 high- or critical-severity vulnerabilities in open-source code

New comment by Smaug123 in "The sigmoids won't save you"

Smaug123 — Mon, 18 May 2026 17:24:04 +0000

I don't think you've addressed the fact that they can do long tasks that aren't in the training set? (And the fact that they're just statistical models isn't very relevant. So am I!)

New comment by Smaug123 in "Prolog Coding Horror"

Smaug123 — Mon, 18 May 2026 08:06:40 +0000

Nah - for example, AIXI is so inefficient that it's literally uncomputable, but it is beautiful.