Viewing profile — robkop

Claude design's prompt is trivial to verify. They bundle it in the frontend bundle and send it on every network request.

CoT legibility largely disappears which is quite concerning from a safety perspective

Just saying you’re not alone, very surprised by the reception given how brutally sloppified the OP is. Interesting problems space but I hope the author just gives dot points next t…

Could you please elaborate a bit more for my understanding? What in particular about this method breaks correct token boundaries? On my first read I read your comment as there are …

I use bedrock with 1M context every day. Not sure this is right

A lot of enterprises were doing that but now they hit the 150 user limit on Claude and are paying seat+api rates. Codex is still going strong but it’s hard to imagine they won’t do…

I've seen a few "Claude tokenizers" floating around lately with all the 4.7 chatter, but most of them just hit the count_tokens endpoint and hand you back a number. You don't actua…

There’s a lot of tradeoffs to play with, those inference ASICs may not carry the gradient but they are still optimised for larger batches and to run any model. They need enough mem…

You can ablate surprisingly large chunks of a model with near to no effect, you can try this easily - download an open weight model in torch. Obviously it’s not ideal but you could…

I can’t speak for the states, but in AU I clearly see a massive displacement of undergrad and junior roles (only in AI exposed domains). I say this as both someone who works with m…

one of their highlights with mythos was it's ability to generate new puns I took a look and honestly they're the first AI puns that aren't bad Times are changing

We’ve got a long way to go in optimising our environments for these models. Our perception of a terminal is much closer to feeding a video into Gemini than reading a textbook of lo…

Rumours say you do something like: Download every github repo -> Classify if it could be used as an env, and what types -> Issues and PRs are great for coding rl envs -> If the sof…

I get this at least once a week. And then once you have to dig in and understand the full mental model it’s not really giving you any uplift anyway. I will say that doing this for …

After adding "Human" as a LLM provider to OpenCode a few months ago as a joke, it turns-out that acting as a LLM is quite painful. But it was surprisingly useful for understanding …

I added a "Human" LLM provider to my local OpenCode a few months ago as a joke, and it turns-out acting as a LLM is quite painful. But it massively improve my agent harnesses dev s…

It's a fair question - I think the fact that they hold abilities (read 200k tokens instantly, can clone themselves, ...) that we don't would suggest they will have quirks and diffe…

https://robkopel.me

Can you elaborate? I would have thought the main driver for the price of a service is the labor?

Does that cost to serve multiple stay the same when conventional sites are forced to shovel ai into each request? e.g. the new google search

I’ve heard too many rumors that much of that adoption is from copying ms i.e. bundling gemini into their office suite

Occam's Razor - this complexity arises from the human nature to try and build consistent abstractions over complex situations. It's exactly what we do in software too. To an outsid…