Ghita
@ghita__ha
Building http://zeroentropy.dev (YC W25)🇲🇦🇫🇷🇺🇸 @Polytechnique | @ucberkeley
Excited to announce our $4.2M seed round led by @Initialized and the release of our state-of-the art reranker zerank-1. zerank-1 was trained using a novel ELO-score inspired training pipeline, that treats query-document relevance like a ranking game (literally, just like Chess!…
The @ZeroEntropy_AI's MCP server is LIVE Context engineering has never been more important to bring the right context to AI Agents performing increasingly complex tasks With ZE, you can do this in one single tool call
Agents without memory of me and what I care about and all the context around me are just not as useful We are so early it is not yet table stakes but it will be
front page of Hacker News with our new chess-Elo-score-inspired training pipeline!
In our rage against "RAG is Dead", @bclavie and I assembled annotated talk notes (Simon Williston style). We take you through the many reasons why RAG is just getting started: single dense vector representations are quite naive Notes in reply hamel.dev/notes/llm/rag/…
Excited to partner with @ZeroEntropy_AI to power their new state-of-the-art, open-source reranker model, zerank!
zerank-1-small was downloaded over 8k times on @huggingface since launching! 🤯 At @ZeroEntropy_AI we released a new state-of-the-art reranker that outperforms every model we’ve tested, and one variant is fully open source. 🔥 Here is where you can access zerank-1 (open-weight)…
if you play the game on easy mode, you eventually get the point where you want to restart on hardest level, only now you have one life, skip to hard mode and try to play the perfect game with no regrets
IN NEWS: ZeroEntropy raises a $4.2M seed round led by @Initialized. We spoke with @ghita__ha on improving AI document retrieval: "The evaluation side of things is very messy and almost everyone relies on manual inspection to make sure their retrieval is working correctly."…
Excited to announce our $4.2M seed round led by @Initialized and the release of our state-of-the art reranker zerank-1. zerank-1 was trained using a novel ELO-score inspired training pipeline, that treats query-document relevance like a ranking game (literally, just like Chess!…
Check out their launch! x.com/ghita__ha/stat…
Excited to announce our $4.2M seed round led by @Initialized and the release of our state-of-the art reranker zerank-1. zerank-1 was trained using a novel ELO-score inspired training pipeline, that treats query-document relevance like a ranking game (literally, just like Chess!…
zerank-1 is available through @mastra_ai now!!
Many of our users doing RAG wanted other rerank providers! Lucky for us @ZeroEntropy_AI just launched a rerank model that pretty much destroys cohere, is way cheaper, and is fast AF. Thanks @ghita__ha and team for contributing this to Mastra!
Morning. Here are our guest call-ins today: – @cpaik (Pace Capital) – @willbruey (Varda) – Joel Becker (METR) – @karimatiyeh (Ramp) – Dylan Parker (Moment) – @iplayedd1 (Consensus) – @ghita__ha (ZeroEntropy) – @elliothershberg (Amplify) See you all on the stream.
TBPN | Thursday, July 10th x.com/i/broadcasts/1…
i'll be on @tbpn at 1:30pm to talk about our model release and seed round!
Some of the most genuinely cracked founders I've met. Congrats!
Excited to announce our $4.2M seed round led by @Initialized and the release of our state-of-the art reranker zerank-1. zerank-1 was trained using a novel ELO-score inspired training pipeline, that treats query-document relevance like a ranking game (literally, just like Chess!…