Viewing profile — k__

Care to elaborate?

"A local Qwen3.5 retrieval model attends over the indexed memory" Hrm.

Seems like this only helps with parallel workloads.

Location: Germany Remote: Yes Willing to relocate: No Roles: Technical Writer, Software Engineer Homepage: https://kay.is LinkedIn: https://www.linkedin.com/in/kay-plößer

Prompt an image or video generator without knowledge in photography or art skills and your results will look sloppy.

I did a bit of research on that in my last job and got the impression that encoder models might help. They are well suited to check input for rule violations and are much cheaper t…

Yeah, I'd assume it's possible to extract all languages as steering vectors from a model and then substract the ones you don't need from its weights. However, that would just chang…

I think, the main issue with German rules is that we haven't embraced digital technology 100%. All these rules would be way less cumbersome if they didn't come with a bunch of lite…

The ratio of good books to slop (AI or not) was far to bad for humans to reasonably filter 20 years ago.

Haha, and I almost felt bad after seeing this chart yesterday.

Half OT: Why do the cache hit rates seem to vary so much between harnesses? I use pi, which is very minimalist, and I get a hit rate of ~99%. Paying like $1 a day for Flash. Yet, t…

On OpenRouter it's 93 TPS.

I'm using pi and my caching is ~99%.

Yeah, it needs quite some hand holding. I didn't do much agent coding and had a mix experience. 1. It would build something that was in the spirit of what I wanted, but unusable in…

I'd take more throughput while everything else stays the same.

While I tend to clear my session after every task, I feel less stressed when my context is as 10% than when it's at 30%

They remove potentially irrelevant details.

As I understand it, they would have to train a whole knew model to hard cap it's context to different lengths. That would be cheaper to train and had cheaper inf, but still a huge …

Right

Yeah, I think the Effect team tried building a compiler for once (TS++ or something) but they abandoned it, as it was too much work.

Do crosswords count?

My 2 weeks with DeepSeek V4: Pro is ~50% more expensive than Flash. Both need babysitting. Plan, split in small tasks, give it docs, types, tests, linter, best practice examples, e…

Thanks! What is the parento frontier?

Half-OT: can anyone recommend a LLM cost calculator that's up to date?

Effect's use of generators is also nice. While looking a bit off, it allows writing imperative business logic.