Viewing profile — criemen

Sweden, Finland and Iceland would be part of any definition of Europe? They're all EU countries, and (irrelevant to that) are now all NATO members too.

Partially, 2.2 Submission workflow W2 deals with this: > Stage W2 The five project-active models, see Table 2, attempted the question. Their answers were compared to the original a…

> Ah, reminds me of good old "There are only 2 hard problems in computer science: cache invalidation, naming things, and off-by-1 errors." You quip, but LLM KV caching (from the ha…

> There's also a runaway effect of model improvement from the discovery, triage and fix data. This is likely already the most potent corpus of curated offensive data ever assembled…

Well is that a statement about the quality of Opus 4.7 or about compose 2.5? :P

> Is there an equivalent ultra-high-end LLM you can have if you’re willing to pay? Or does it not exist because it would cost too much to train? I guess at the time that was GPT-4.…

> it's them trying to push the models to burn less compute I'm curious, how does using more tokens save compute?

Pretty cool if true!

> What people don't realize is that cache is free I'm incredibly salty about this - they're essentially monetizing intensely something that allows them to sell their inference at p…

I tried ChatGPT over the holidays (paid) vs. claude.ai (paid). After trying some prompts that worked well on Claude in ChatGPT, I understand why people are so annoyed about AI slop…

> Out of curiosity, what are some good use cases for a MBP now with the MBAs being so powerful? Local software development (node/TS). When opus-4.6-fast launched, it felt like some…

Even if was copying sqlite code over, wouldn't the ability to automatically rewrite sqlite in Rust be a valuable asset?

> I had assumed that reasoning models should easily be able to answer this correctly. I thought so too, yet Opus 4.6 with extended thinking (on claude.ai) gives me > Walk. At 50 me…

This is amazing. At $workplace, we have a script that extracts a toolchain from a GitHub actions windows runner, packages it up, stuffs it into git LFS, which is then pulled by baz…

One other thing I'd assume Anthropic is doing is routing all fast requests to the latest-gen hardware. They most certainly have a diverse fleet of inference hardware (TPUs, GPUs of…

> aka: For those not living in 2026, we have uncovered a new clue to the mystery of where all the low-power DRAM chips have suddenly vanished to! I love the writing style!

What's the power hookup to just boot one rack? I'd imagine that's more than you get anywhere in residential areas for a single house.

> I’m currently using a mix of Zed, Sublime, and VS Code. Can you elaborate on when you use which editor? I'd have imagined that there's value in learning and using one editor in-d…

> This takes a fairly large mindset shift, but the hard work is the conceptual thinking, not the typing. But the hard work always was the conceptual thinking? At least at and beyon…

The large open-weights models aren't really usable for local running (even with current hardware), but multiple providers compete on running inference for you, so it's reasonable t…

It used to be that the answer was logprobs, but it seems that is no longer available.

> Of course there is undefined behavior that isn't security critical. But undefined behavior is literally introduced as "the compiler is allowed to do anything, including deleting …

I've been thinking a lot about that lately, and I agree. I used to be hard in the "You can't solve social problems with technical solutions", but that's not the whole truth. If peo…