i have something to release/share tomorrow that i think is very badly needed and has been so for a few years - it’s a tiny start and won’t be complete but i hope people will find it as useful and fun as i have enjoyed producing it

as someone who proudly reposted the release before it had any traction and who loves the team, y’all here are massively and absurdly overhyping an otherwise perfectly good (even great) release calm down and, unironically, be calibrated for once..!

dspy.GEPA used in pretraining data curation in the new Microsoft AI effort :-)

overwhelming evidence for late interaction / multi-vector models yet again :-) > even after finetuning, single-vector models lag far behind multi-vector embeddings, which achieve significant performance gains and exhibit greater robustness to catastrophic forgetting.

The “grep-is-all-you-need” nonsense arguments arise from the fact that too many people think neural search means single-vector IR, which do in fact suck. But we’ve known that since 2019. Quoting @aaxsh18, CEO of Mixedbread: > late interaction cant stop winning

Of course not. In fact, my lab is simultaneously building RLMs as the next paradigm for LLMs *and* developing the next paradigm for retrieval (stay tuned!). Retrieval will not go anywhere: if you have a large corpus with, say, billions of tokens over which you issue many queries, you necessarily need to build some index data structures that enable fast sub-linear access. RLMs may internally choose to build such an index when it proves to be an effective tool, but fundamentally RLMs are about long one-off context. You wouldn’t typically put an RLM over a million documents and expect that to be the optimal system design. (Thank you for the question @jayitabhattac11 !)

IMO, RLMs are as “language model”-y as modern “LLMs” or Reasoning Models are truly “statistical models of language”. All three are a bit of a stretch BUT in the same way. Pedantically, all three are language processing systems, eg recursive/reasoning language processing system.

> You’ll implement ColBERT to understand multi-vector search [and] apply ColPali for patch-level image retrieval. So happy to see the great folks at @DeepLearningAI @AndrewYNg host a course on late interaction (ColBERT, ColPali et al) after their short course on DSPy :D

Martin @martin_casado and I had a fun hour-long chat about why we need an AI software layer, and why that's true even if AGI arrives. This is basically my take on why "the model" is definitely NOT "the product", though models are one way you may decide to implement some products

The labs don't want you to know this (jk) but they have no clue how to best prompt their own models either. To some approximation, you just pre-/post-train it on a lot of data, intervene on certain behaviors, and what comes out is what comes out.

Ok, I'll say it. One of the biggest challenges facing DSPy is the lack of competition. As far as I can tell, there's just no other serious programming model for general-purpose, declarative AI programming. I can spend hours listing the costs/downsides of this, not the least of which is the implicit comparison against LLM libraries in too many people's minds. Another downside is that it's really hard for an entity to improve by competing against baselines that suck. Too easy to be complacent, so we have to start & keep challenging ourselves.