[WhitneyLand]

Does anyone write anymore?

It’s difficult to read posts that rely so heavily on AI generated prose.

Everything’s a numbered/bulleted list and the same old turns of speech describe any scenario.

That aside, what’s really keeping this from being useful is showing some results. How well does this approach work? Who knows. If the data is sensitive, seeing it work on an open source repo would still illuminate.

Also, we hear lots elsewhere about the limitations of relying on embeddings for coding tools, it would be interesting to know how those limitations are overcome here.

[antonybrahin]

Interesting point on embedding, I'll research more on that. But as of now, in my knowledge, that's the best available way of identifying close matches. I'll try to find if there are any alternatives.

[WhitneyLand]

Antony, you’d be right to call me out on providing a source. So in case it’s helpful, this is the last place I recall the subject being discussed:

RAG is Dead, Context Engineering is King

https://www.latent.space/p/chroma

[antonybrahin]

I will check it out and make the updates necessary. Thank you for sharing that.