开启时会模糊预览图，关闭后正常显示
Building Baleen was extremely painful. I think the final recipe alone involved training like 12 models in a sequence. That was the motivation for developing DSPy so you can build these modular LLM systems/agents and allow them to self-train without having to do all that.
Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.
big fan of @JustinLin610 's work: see his keynote https://t.co/vJB7Gf7MIt at AIE!
@JustinLin610 btw a good perspective is: coding agent perf = read the right files + write the right diffs swe-grep is the fast read model swe-1.5 is the fast write model when in IDE, 3 fast turns with human near SOTA > 1 slow turn with SOTA
Yup I was there live. The kids have zero idea how to press. Nwanneri included
Founder | Author | Speaker Building @beltstripe I'm Not The Man Of Your Dreams. Your Imagination Wasn't This Great.
If a problem seems intractable, it's almost always because your specification of it is vague or incomplete. The solution doesn't appear when you "think harder". It appears when you describe the problem in a sufficiently precise and explicit fashion -- until you see its true form. A well-specified problem has a small, legible solution space.
Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
RT @CBSEveningNews: Hurricane Melissa has left dozens dead and widespread destruction across Jamaica, Haiti and Cuba, as it continues to th…
Your source for original reporting and trusted news. 📺 CBS | Streaming on the CBS News app | @ParamountPlus
Haha again. Amazing
Founder | Author | Speaker Building @beltstripe I'm Not The Man Of Your Dreams. Your Imagination Wasn't This Great.