Viewing profile — runeblaze

tbh the summarized thinking with encrypted raw thinking is there for many purposes; it is there to: 1. make distillation much harder 2. safety: prevent modifications to the thinkin…

links to two papers with at least enough apparent quality and novelty to get into ICLR 2026 > So basically... openrouter :skull: i now really wonder how many people of the public u…

> visual similarity > SigLIP 2 Maybe visual-semantic similarity is more appropriate? Nonetheless the design is fantastic

I mean I used to work on model reliability with my little PhD degree and the models i manage go down all the time. Some profs have a team of PhDs and things go to shit all the time…

1. openrouter is API usage. There is obviously consumer side 2. people often use openrouter for the sole purpose of using a unified chat completions API 3. OpenAI invented chat com…

Schemas can get pretty complex (and LLMs might not be the best at counting). Also schemas are sometimes the first way to guard against the stochasticity of LLMs. With that said, th…

Resouce-affording, if you are chasing the frontier of some more niche task you redo your training regime on the new-gen LLMs

Is it though? There is a reason gpt has codex variants. RL on a specific task raises the performance on that task

Sure never again is totally fair and I am sure a lot of people hate it. I was mostly objecting to the radioactivity of it. Your friends will be more like “I am looking to sell my T…

I think radioactive is a strong word here… I have talked to a lot of people in tech

Reading what you wrote scares me

> And if for some ungodly reason you had to do it in Python I literally invoke sglang and vllm in Python. You are supposed to (if not using them over-the-network) use the two faste…

Agreed, I am surprised he is happy to stay this long. He would have been on paper a far better match at a place like pre-Gemini-era Google

I don't know the data distribution, but are you sure that's generated by an Adobe model? I can only see that it is in Stock + it is tagged as AI generated (that is, was that image …

Emmmm sure, but throw this to a human artist who has not heard of Indiana Jones and see if they draw something alike.

I work in this space. In traditional diffusion-based regimes (paired image and text), one can absolutely check the text to remove all occurrences of Indiana Jones. Likewise, Adobe …

My personal mantra (that I myself cannot uphold 100%) is that every dev should at least do the exercise of implementing binary search from scratch in a language with arbitrary-prec…

each text token is often subword unit, but in VLMs the visual tokens are in semantic space. Semantic space obviously compresses much more than subword slices. disclaimer: not exper…

beats me. I spent so much time learning what a fundamental group is and I still cannot tell ppl what a fundamental group is convincingly. I can’t even make stuff with fundamental g…

Ummm guys when we talk about memory access in theory can we just be rigorous and talk about the computational model? The real RAM model “in theory” tells me that memory access is O…

Of course it seems to be the same person to have done minecraft inside minecraft using redstone :)). peak!! done it again

Yea experience is very useful (it is very hard to exert influence without power and be the tech lead of a team unless you have some corporate experience) but at some point one need…

Python types - all the onus of static types, with none of the power of calculus of constructions. /s

sure of course one does not need types to do natural deduction… if you throw what you showed me to your average maths undergrad in the US they will get confused — I truly don’t see…

> How proofs work is really simple idgi. If you do your 101 logic class often you learn natural deduction, and how do you formalize natural deduction in a computer system? (Hint: t…