Viewing profile — machinelearning

Training is expensive so I wouldn't necessarily call it "pragmatic". - the tool's goal is actually to provide a lightweight, practical way to avoid wasting training cycles on bad d…

"Most ways of constructing accurate models mathematically don’t actually work" > This is true for almost anything at the limit, we are already able to model spatiotemporal dynamics…

> The reason is that it makes the essay easier to read. It's less work to read writing that flows well. How does that help the writer? Because the writer is the first reader Note t…

So one thing to note is that the essay mentions that it refers specifically to "writing that is used to develop ideas" vs. "writing meant to describe others ideas". The way I inter…

The issue with this article is that it is very imprecise. Are the standards for whether something “sounds bad” based on the average person’s reading or the intended audience. In it…

> “So here we have the most exciting kind of idea: one that seems both preposterous and true.” Am I missing something or is the “seems true” part taking too many liberties here? If…

What's a use case are you interested in re: video?

This is a good problem to solve but the approach is wrong imo. It has to be done in a hierarchical way to know what you attended to + full context. If the differential vector is be…

No, you've only discussed the Retrieval part of RAG, not the generation part. The current workflow is to use the embedding to retrieve documents then dump the text corresponding to…

Nope that’s not how most rag systems work today. I looked at pgvector and couldn’t find anything similar. Do you have a link? Or maybe you misunderstood what I was taking about

Both RAG and infinite contexts in their current states are hacks. Both waste compute because you have to re-encode things as text each time and RAG needs a lot of heuristics + a se…

This is a simple version of the tree search approach that people suspect Q* is

As someone who studied math, I approve of this video. Summary available here: https://www.askyoutube.ai/share/6533668f27f67cda427ab90f

https://www.askyoutube.ai/share/6521aa6077733b7c0ad24b55

Its much faster now and a share function has been added for pre-loaded examples

Added

Added

That's reasonable, planning to add it tomorrow

Thanks for the feedback, I haven't done much optimization in regards to the summary. The screen real-estate of the summary has to be small so it is limited in the amount of informa…

Glad that it worked well for you! I don't have any general advice that would be useful but that sounds like an interesting project