Composer 2.5 is now available inside Grok Build.
Composer 2.5 is a fast, highly intelligent model that excels on long-running tasks and following complex instructions.
Spain’s National Court has charged former Spanish PM José Luis Rodríguez Zapatero with money laundering, influence peddling and other criminal offenses committed in connection with the €53 million bailout of Plus Ultra airlines.
https://t.co/Z6z8r8q6DD
BM25 efficiently scores text, but relevance often depends on more than text (recency, popularity, PageRank)
we score non-text attributes as clauses in the same MAXSCORE plan that evaluates BM25 → better first-stage relevance, still scales to 100M+
https://t.co/KY6hbOJuI7
We've been developing a multi-agent system that builds and maintains complex software autonomously.
Recently, we partnered with NVIDIA to apply it to optimizing CUDA kernels.
In 3 weeks, it delivered a 38% geomean speedup across 235 problems.
I've heard some people say that Composer 2 is "just Kimi 2.5", which is easy to disprove if you look at any benchmarks... or, huh, if you run the model for like 30 seconds. Anyway: this paper shows the humongous training effort that went behind our model. Please check it out.
Cursor can now search millions of files and find results in milliseconds.
This dramatically speeds up how fast agents complete tasks.
We're sharing how we built Instant Grep, including the algorithms and tradeoffs behind the design.
@chacon My mom texted me to let me know she “gave a hearty” to your “very nice tweet”. She thinks you’re a very nice man, FYI. This all began because GitHub HR had my parents’ address on file and you mailed her several Christmas cards with pictures of your children.
@gustojs@ericzakariasson@leerob Most of these were 1.5 actually, I wrote the post earlier this year! Of course this is only for the visualizations. The actual text is 100% human-grown organic. :)