Viewing profile — mbowcut2

I made myself reason it out, and came up with the exact same intuition. You need a sequence of 2n moves (n down moves, n over moves), but the sequence is completely determined by w…

Totally agree. Granting exemptions feels like trying to have their cake and eat it too. If regulations mean anything they need to be enforced so we can see the real downstream effe…

Gotta hit that docker system prune -a

Loved him in Secondhand Lions.

If you thought we were getting bad bugs before, just wait until the 90% agent-coded PRs start landing. We're gonna have multiple crowdstrike-level blowups.

It's an interesting concept, but I'm skeptical about how feasible this is. How much design/legwork/intervention will Seth actually contribute during the entire process? I'm thinkin…

Wow, I didn't know about the "skills" feature, but with that as context isn't this attack strategy obvious? Running an unverified skill in Cowork is akin to running unverified code…

It makes me wonder about the gaps in evaluating LLMs by benchmarks. There almost certainly is overfitting happening which could degrade other use cases. "In practice" evaluation is…

Seems like the less sexy headline is just something about the sample size needed for LLM fact encoding That's honestly a more interesting angle to me: How many instances of data X …

I'm not surprised. People really thought the models just kept getting better and better?

it looks like the 2nd and 3rd bar never got updated from the dummy data placeholders lol.

It's not a new problem (for individuals), though perhaps at an unprecedented scale (so, maybe a new problem for civilization). I'm sure there were black smiths that felt they had l…

I've had similar experiences with vanilla ChatGPT as a DM but I bet with clever prompt engineering and context window management you could solve or at least dramatically improve th…

You can, and there has been some interesting work done with it. The technique is called LogitLens, and basically you pass intermediate embeddings through the LMHead to get logits c…

The problem with embeddings is that they're basically inscrutable to anything but the model itself. It's true that they must encode the semantic meaning of the input sequence, but …

LLMs are better at LaTeX than humans. ChatGPT often writes LaTeX responses.

I think I agree with you. My only rebuttal would be it's this kind of thinking that's kept any leading players form trying other architectures in the first place. As far as I know,…

I read this as "pirate space industry" and got real excited.

It's interesting how I couldn't tell whether the rocket was 1m tall or 10m tall in this video. Turns out it's actually 6m tall per the link.

Nah, I think they made it model agnostic, which is kinda smart.

To a topologist, everything is topology.

Pack it up boys, they finally made the killer app.

I had a smart TV that gradually got slower and slower until it became basically useless. I figured it was just running out of RAM as apps got larger with updates over the years.