Viewing profile — lopuhin

Qwen3.5 is able to output click coordinates and bounding boxes just fine, as values normalized to 0..1000, I’d hope Qwen3.6 didn’t loose this capability.

For that you only need high throughput which is much easier to achieve compared to high latency, thanks to batching -- assuming the log lines or chunks can be processed independent…

On whether this accounts only the final output layer -- once the first token is generated (i.e. selected according to the modified sampling procedure), and assuming a different tok…

That's impressive how you figured out the reason for the difference in list of floats vs list of ints container size, framed as an interview question that would have been quite dif…

Context window size of 400k is not new, gpt-5, 5.1, 5-mini, etc. have the same. But they do claim they improved long context performance which if true would be great.

you can rent them for less then $2/h in a lot of places (maybe not in the drawer)

I find OpenAI's new flex processing more attractive, as it has the same 50% discount, but allows to use the same API as regular chat mode, so you can still do stuff where Batch API…

it's pretty difficult to package native python dependencies for wasmtime or other wasi runtimes, e.g. lxml

Crazy amount of breakage... Here is a PR which reverts this: https://github.com/pypa/setuptools/pull/4911 Interesting that maintainers of setuptools still only postpone the depreci…

Congrats on the launch! How much does it cost? And what is the sandboxing technology?

I find it strange that the author is really happy with the quality of string comparison here https://pgaleone.eu/ai/coding/2025/01/26/using-ai-for-coding... and while it would kind…

It's a 600B+ mixture of experts and yes it's described in the paper, GitHub, etc.

Why is this doubtful, did you spot any suspicious things in their paper? They make the weights and a lot of training details open as well, which leaves much less room for making st…

With distilled models being released, it's very likely they'd be soon served by other providers at a good price and perf, unlike the full R1 which is very big and much harder to se…

I don't think so, what they show on CS video is exactly the Dust2 map, not just something similar/inspired by it.

I think GraalPython does have a GIL, see https://github.com/oracle/graalpython/blob/master/docs/contr... - and if by "there is no such thing on those platforms" you mean JVM/CLR no…

Curious which model was used? Sorry if I missed that. Looks like an important detail to mention when doing an evaluation.

Also I don't think you can use NIM packages in production without a subscription, and I wasn't able to find the cost without signing up. Also NIM package for Mistral Nemo is not ye…

The README says they plan to add llama.cpp support which should cover a lot of targets, also they have tinygrad already integrated I think.

Not quite the same, OpenAI was initially quite open, while Ilia is currently very explicitly against opening or open-sourcing research, e.g. see https://www.theverge.com/2023/3/15/…

yes looks like a bug in the example to me, feel free to report to https://github.com/fchollet/ARC-AGI/issues :)

Really nice to see no-GIL Python become closer and closer to reality.