Viewing profile — activatedgeek

Congratulations on the strong reception of min-p. Very clever! We may be talking about two orthogonal things here. And also to be clear, I don't care about theoretical guarantees e…

That has been my understanding too. More generally, a verifier at the end certainly helps. In our paper [1], we find that asking a follow up question like "Is the answer correct?" …

Reasoning tokens are indeed billed as output tokens. > While reasoning tokens are not visible via the API, they still occupy space in the model's context window and are billed as o…

This effect is very interesting. Veritasium covered this effect in a video [1] for the interested. [1]: https://www.youtube.com/watch?v=aIx2N-viNwY (2016)

I use Astro + Cloudflare Pages for my website [1]. I document the key bits of my stack here [2] for completeness. I've been very happy with Astro because it is a good example of lo…

The best thing that one can do for themselves to develop the creative "muscle" is to _own_ their time. Unfortunately, I am yet to feel even close to such a breakthrough. I think ve…

The fact that Pyinfra does not currently support a feature which can be implemented using Pyinfra philosophy does not make it different than Ansible. I believe that was what the pa…

Any kind of provisioning doesn't seem too far a step though. It is just another "operation" with its own state management logic.

I current use Ansible to setup both local and remote hosts. I've been very happy with it, and love that Pyinfra intends to support the Ansible connector. My main gripe with Ansible…

If you use HuggingFace models, then a few simpler decoding algorithms are already implemented for `generate` method of all supported models. Here is a blog post that describes it: …

Makes sense. Thank you for a the QS reference!

I hesitate to the use description as "think," just biasing correlations for subsequent generations. In any case, there is at least one work that shows that CoT may not be necessary…

I see. Following up on this, for the sake of being explicit: was the bottleneck here getting all the data sources in place (perhaps for instance access permissions, legal, etc.), w…

I want to point out a tweet [1] that is very relevant to the miracle of CoT, and probably a simpler explanation. > Let's think "step by step"! > Another tidbit I like about data an…

In AI/ML research, text to SQL always sounded to me of merely academic interest, in the sense that the outputs are easily verifiable and make for a good proof of concept of a langu…

I looked at Ollama before, but couldn't quite figure something out from the docs [1] It looks like a lot of the tooling is heavily engineered for a set of modern popular LLM-esque …