ykumards

IMO it would be hard to reproduce the results using autoresearch setup.

To get CLIP to work properly we typically need large batch sizes. So the experiments in the original paper were quite heavy, and ran parallel across 8 GPUs.

Sorry I could have worded this part better.

The docker container didn’t have network access. Claude didn’t have permission to execute anything other than the run.sh bash script, which would orchestrate the docker run

That’s true! It felt a bit flippant to give medical data to an agent. Also, I wanted to see if the model would work in other domains!

Thank you, glad you liked it!

I'm subscribed to Huggingface's Daily Papers newsletter but going through each paper individually was a chore.

So I created a GH workflow to pull the papers, use an LLM and TTS to generate the podcast daily.

Hope you like it!