Keep on to blur preview images; turn off to show them clearly
Finally systematic evals based on synthetic exercises slowly becoming the norm for architecture evaluations (from Kimi-Linear). Many thanks to Physics of Language Models for leading the way.
Getting out of HellaSwag dark age, one step at a time.
RT @nrehiew_: Thankfully, theres a really nice glossary in the KIMI Delta Attention paper that covers most of the notable variants https://…
We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
I love the way Tibo and team are so methodically going through every inch of the system to try to track down user feedback.
AI is cool i guess
RT @racer_dot_fun: while you're launching tokens, we're launching the Solana Grand Prix 🏁 drop your wallet if you want in the pit crew for…
CEO @dotfunlabs - crypto games that drive culture ⿻ Crew Chief @ Solana Grand Prix / @racer_dot_fun
看着很不错 想买了🤣
学AI找小互，找小互，上 https://t.co/4PVaHEr5r3 ...
RT @thdxr: glm also beat it, both in score and speed getting more convinced at this point that RL teams scare everyone away by saying a bu…
building workers observability @cloudflaredev, prev founder @baselimehq (acquired by cloudflare), prev aerodynamicist