Pinned
Engram
@EngramLab
scaling compute on your context
In collaboration with @harvey, we’re excited to build a new kind of agent environment to reflect realistic knowledge work: an entire synthetic law firm, Calderwood & Harkness, with over 100M (!) tokens of documents and 250 client cases. 💼 Today’s AI models know a lot about the- Our founder @jxmnop recently issued some unfounded claims that got community noted. We deeply apologize for the confusion caused by his original post, the follow-up post, and the follow-up to the follow-up post. Nevertheless, we stand by his conviction in his own takes---and inpeople are underestimating what a big deal this is this is the ONLY open-weight model that's trained without distilling from OpenAI or Anthropic • Kimi distills • GLM distills • Qwen distills • Nemotron distills (Kimi & DeepSeek, which counts) basically a fully different
- We are thrilled to announce Engram's pivot to dairy farming. Our primary activity will be fostering 🐐s like @jxmnop -- who recently won an ICML outstanding paper award for his work on language model memorization and capacity! We're incredibly proud to work with Jack every day,my paper won an award at icml 😁 some thoughts: • this work was rejected from NeurIPS. i cleaned it up a small amount and it got great reviews from ICML! don't give up • ICML received 24k submissions and only gives out 7 awards, which is crazy. feeling grateful • i
- John and Jordi from @tbpn are in the pretraining data, but most people aren't. Frontier models train on trillions of tokens and still have no idea who you are. We're fixing that. Thanks for hosting us – and banging the gong for Engram. This meant more than you'll ever know.
