Yasyf Mohamedali

It’s been thoroughly shown at this point that having LLMs author prompts for themselves (free-form that is, not DSPy-style) is disastrous, and that LLM-authored skills actually make things worse, but writing code is what these next-token-predictors excel…

Please don’t rm… One of the unfortunate externalities of prompt engineering working so damn well is we often forget to reach for other tools in our toolbox.

Anthropic’s recent release of Computer Use for claude-3-5-sonnet-20241022 is super exciting—we’re finally getting good abstractions for “bring your own compute” with SOTA LLMs.

Remember PoisonGPT?

Bringing Go’s defer statement to Python!

Recently, Pinecone announced support for Sparse-dense embeddings, allowing for hybrid vector search.

I saw @VictorTaelin’s tweet recently on increasing the effective context window for GPT-* by asking the LLM to compress a prompt which is then fed into another instance of the same model.

I was inspired after seeing @NaderLikeLadder’s post “Using ChatGPT to make Bash palatable”.