Viewing profile — suryabhupa

In practice, and at scale, that's exactly what having and tokens allow you to easily and programmatically do.

The announcements are live on Twitter! See this for example: https://x.com/suryabhupa/status/1806342617191379167

Surya here from the core Gemma team -- we can think of a distillation loss as learning to model the entire distribution of tokens that are likely to follow the prefix thus far, ins…

This is really remarkable! How hard do you think it will be to support new models, i.e. does the tooling you’ve built generalize to you being able to serve other large scale models…

Hi everyone! One of the creators of DFL here. In an attempt to more deeply understand fundamental concepts in machine learning, we designed Depth First Learning. It's a pedagogy fo…

Many machine learning and reinforcement learning models are susceptible to adversarial attacks; it's not unique to deep learning. However, because so many systems that are currentl…

There are talks of incorporating this into Excel at some point in the future, but it may take a _while_ before it can be fully productionized.

That would be pretty cool to see what it learns, but I don't think we've tried that :P

That's one manifestation of this kind of research being used in real life by programmers around the world. :)

I'm not too familiar with evolutionary computation methods, but I imagine the approaches may be similar in nature.

Theorem solving is very closely related to program induction (we just change the grammar). Just as with Python, the underlying search space would be incredibly large, and while in …

It turns out the full grammar of Python (and almost all real programming languages) is quite large; this is very early and new work in neural program synthesis, and so we chose a p…

Eventually, yes.

One of the authors here -- would love to answer any questions about the work! :)

How do you imagine going about this?

The idea is that even there's a policy network that is able to decide at some point what the best possible move is, the tree search is done to refine this choice and to "evaluate" …