Viewing profile — skerit

"That's on me."

Out of my 7 simultaneous sessions (my usage limit reset is tomorrow, so I have some lesser important projects to use my tokens on) there is still 1 session purring on. So there's a…

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.

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, a…

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 …

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 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 …

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 re…

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. (B…

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 b…

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 ev…

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'…

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

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…

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

> the improvements are getting smaller and smaller The AI haters have been saying this for 2 years now.

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

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?

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 m…

Yeah, that approach makes the most sense.

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

> 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?

I'm currently reverse engineering a few games too. It's quite easy with AI now. But I'm worried about the legality of it all. Any thoughts on this?

I've been working on something like this too, for quite a while! Though I'm trying to get a non-quadratic-attention LLM (or SLM) up and running. And anyway, I think the most import…

I've been creating my own little from-scratch LLM for months now with Claude's help. I can safely say I learned a thing or two along the way.