Hacker News: skerit

New comment by skerit in "Hannah Fry Wins the Leelavati Prize in 2026 for Mathematics Outreach"

skerit — Sat, 25 Jul 2026 08:02:11 +0000

And on her podcast with Vsauce she said the reason they chose that town was because their budget was so low and they could sleep over at a crew member's family there.

New comment by skerit in "Claude Opus 5"

skerit — Fri, 24 Jul 2026 17:31:01 +0000

Interesting, they finally support `system` messages anywhere in a chat conversation:

> Mid-conversation system messages are available on the Claude API, Claude in Amazon Bedrock, and Google Cloud. > > This feature is available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5. No beta header is required. This feature is not available on Claude Sonnet 5; use the top-level system field instead.

For nearly all models EXCEPT Sonnet 5? That is weird. How old is Sonnet 5 really?

New comment by skerit in "OpenAI reduces Codex Model Context Size from 372k to 272k"

skerit — Sun, 19 Jul 2026 12:05:12 +0000

No matter how good compaction is, on some big projects it needs to read a lot of files. In my experience the first 200.000 tokens go FAST, but after that it slows down. Most of my Fable sessions don't go over 500.000 tokens, I don't need to compact once. But when I use Codex a single session has to compact over and over again.

New comment by skerit in "Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniability"

skerit — Mon, 06 Jul 2026 23:50:38 +0000

I tried using `/goal` when it just came out, but back then they used Haiku for it. And if your main model is a 1M model, Haiku can't even read that much. So my /goal always failed. (I instead went for an elaborate /loop-scheduled message)

New comment by skerit in "Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniability"

skerit — Mon, 06 Jul 2026 15:23:24 +0000

I think the improvement on how it codes is pretty much represented correctly by the benchmarks (a nice bump, but not some crazy leap)

But where it really shines is in how NOT lazy it is. Fable requires less hand-holding. And I can understand how someone who uses Claude-Code sparingly and with very focused prompts would not see a lot of improvement there.

But simple example: if you ask Opus to do a review of the codebase (with a short prompt and not too much guidance), I've had it basically read the `git log` output, do a simple `ls` and have it declare "Everything looks great! No problems found!", when Fable really does what you would expect it to do.

And you might think: "oh, so it's just capable of handling crap prompts?", well sure. But even if you make THE PERFECT Opus plan (a plan that would take many turns/hours to finish), Opus will fake out, say everything is done, and then you see that half of the plan was deferred, half of the functions are ridiculous stubs, ...

If you give the same plan to Fable, it'll just DO IT. And it WILL get it done. And in the end it'll tell you "Oh, I also found 30 other bugs and I fixed all of them properly" (where Opus would have started crying, or WORSE, worked around the bugs)

New comment by skerit in "Command and Conquer Generals natively ported to macOS, iPhone, iPad using Fable"

skerit — Sat, 04 Jul 2026 20:55:24 +0000

I've been doing something similar for some of my favourite older games. But the "byte for byte" claim has me worried. Isn't simply decompiling the sourcecode from the binary and releasing that problematic?

It's not the "clean room" approach and companies could still claim it violates some kind of copyright and get it taken down.

New comment by skerit in "Command and Conquer Generals natively ported to macOS, iPhone, iPad using Fable"

skerit — Sat, 04 Jul 2026 20:50:50 +0000

I thought it was just Opus 4.7 and 4.8 that did this. Do other models do this too?

Anyway: in my case Opus absolutely did not follow a similar instruction in the CLAUDE.md file. (But then again: it hardly followed _any_ CLAUDE.md instruction properly)

New comment by skerit in "Claude Fable 5 Promotional Access"

skerit — Wed, 01 Jul 2026 21:08:07 +0000

That's not true, but it's their own fault for being so utterly terrible at communication. It only drops back to Opus for some prompts, just like before. The longer blogpost was a bit less vague about this.

New comment by skerit in "Claude Fable 5 Promotional Access"

skerit — Wed, 01 Jul 2026 21:05:52 +0000

Before Fable got pulled, they claimed their goal really was to keep it around in the subscriptions in some way, they just didn't know when it would return. This time there isn't even a single mention of this. It's just "This is a promotion, and it's going away". Like how the hell can this corporation be so fucking bad at communication?

New comment by skerit in "Fable 5 is Back"

skerit — Wed, 01 Jul 2026 20:25:56 +0000

I just don't really understand the entire strategy behind this. Or their horrible, horrible communication.

Because right now it's as if Fable/Mythos 5 is "the end of the line". It's as if this is the best their models are ever going to be. So what the hell are we going to get next? All of their models will forever inch closer to Fable, but never reach it? That doesn't make any sense.

It all seems so dramatic. Instead of just saying honestly "Look, this model is a beast to run, but we're striving to reach the same quality in a cheaper model down the line" all we get is "Oh my god, it's so big and scary, and it costs so much to run, woe is me!"

New comment by skerit in "Claude Sonnet 5"

skerit — Tue, 30 Jun 2026 18:35:05 +0000

This is why Fable was so good. It followed instructions and it was in no way lazy.

New comment by skerit in "Words Are a Byproduct of Consciousness. For LLMs, It's Backwards"

skerit — Tue, 30 Jun 2026 14:43:31 +0000

But LLMs aren't just shuffling words around. Words (tokens) are the "human interface" at the edges. Text input gets embedded, then there's this huge latent-space computation in the middle, and only at the tail end does that get converted back into word/token probabilities. So just saying that "words are the source" isn't entirely correct and feels misleading.

New comment by skerit in "Anonymous GitHub account mass-dropping undisclosed 0-days"

skerit — Sat, 27 Jun 2026 16:49:38 +0000

I immediately saw the Ghidra one and was thinking: huh?

New comment by skerit in "Why current LLM costs are not sustainable"

skerit — Fri, 26 Jun 2026 09:05:38 +0000

> the improvements are getting smaller and smaller

The AI haters have been saying this for 2 years now.

New comment by skerit in "Claude Tag"

skerit — Tue, 23 Jun 2026 17:52:38 +0000

And here I was thinking we'd be getting Sonnet 5. Or maybe even poor old Fable back. Not this junk.

New comment by skerit in "Oracle shed about 20k roles globally in the last year"

skerit — Tue, 23 Jun 2026 12:22:43 +0000

Which AI bubble? The stock bubble one or the imagined "one day all the LLMs are going to disappear from the face of the Earth" one?

New comment by skerit in "Gemini models increasingly stucking in thinking loop"

skerit — Tue, 23 Jun 2026 09:19:23 +0000

Was this not the case earlier? I've had it stuck in loops from day 1, even when Gemini 3 came out. I've never been able to actually use it for anything because it goes absolutely mental after a handful of turns.

New comment by skerit in "DOS Game "F-15 Strike Eagle II" reversing project needs DOS test pilots"

skerit — Sat, 20 Jun 2026 19:01:24 +0000

Yeah, that approach makes the most sense.

New comment by skerit in "DOS Game "F-15 Strike Eagle II" reversing project needs DOS test pilots"

skerit — Sat, 20 Jun 2026 19:00:32 +0000

Oh yes, of course. I was talking about reverse engineering the code only. Requiring the official assets is a no-brainer.

New comment by skerit in "DOS Game "F-15 Strike Eagle II" reversing project needs DOS test pilots"

skerit — Sat, 20 Jun 2026 18:59:26 +0000

> it would be extremely easy for the rightholders to claim that both agents have most certainly ingested the binary during their training phase

Ingested the binary?