ZeroEntropy (YC W25)

@colinevans @ghita__ha @OpenAI @GeminiApp @Alibaba_Qwen @huggingface @awscloud Thank you Colin!

@ghita__ha @ZeroEntropy_AI @OpenAI @GeminiApp @Alibaba_Qwen @huggingface @awscloud Excited for this model, and for you @ghita__ha and Nicholas!

zembed-1 is finally here! 🔥 The world's best embedding model, by @ZeroEntropy_AI It outperforms @OpenAI , @GeminiApp , @Alibaba_Qwen , and Voyage's latest embeddings on 100+ languages, and across verticals. Available now via our API/SDK, @huggingface, and @awscloud Marketplace. Full launch post in the thread for benchmarks and more about our secret sauce 👀 We're building the entire retrieval stack... and we're just getting started. 🤫 PS: We're giving out free credits to try it, just comment on the post or DM me!

@ghita__ha @OpenAI @GeminiApp @Alibaba_Qwen @huggingface @awscloud The best embedding in the world

live from @MIT where @ZeroEntropy_AI 's CTO is presenting our latest zElo paper and reranker model! @npip99

@ghita__ha @MIT Join us: ycombinator.com/companies/zero…

shout out to @ghita__ha and the @ZeroEntropy_AI team for organizing!

We just built a free tool to ask questions over the 2025 @NeurIPSConf research papers. Try it out at neurips dot zeroentropy dot dev No signup, no credit card, just the best way to learn more about this year's papers!

It’s always amazing to see small teams outperform companies with $100M+ in funding, and even more amazing when you get to be a part of it. 😅 Stoked that we were able to support @ZeroEntropy_AI on training their state of the art reranker model family! Read here about the zerank family: tensorpool.dev/blog/zeroentro… @ghita__ha @npip99

@TychoSvoboda Delightful working with @TensorPool

@ghita__ha zerank-2 will improve any search or retrieval system!

We are very excited to release zerank-2, @ZeroEntropy_AI 's newest reranker model. 🔥 It shows major improvement on the 5 most common RAG failure modes below. Existing rerankers consistently fail on seemingly “simple” tasks: 🔢 Comparing numbers and date: “Biggest deals closed after 04/2024.” 🗄️ Aggregation: “Top 10 objections of customer X?” 🌍 Multilingual: Major pain point, especially non-English to non-English. 🙏 Instruction-Following: “Find the *counterargument* of the claim in the transcript” 🥇 Calibrated scores: You ask "what should I cook for dinner?", and "I am allergic to nuts" scores too low for your threshold. Many rerankers overfit public benchmarks, and don’t generalize to these real issues. zerank-2 outperforms existing rerankers considerably on all of these failure modes, in real production environments. With zerank-2, you get: * 15% improvement vs Cohere rerank 3.5 on Arabic/Hindi (Miraql dataset) * +12% NDCG@10 on sorting tasks (new open-sourced eval set) * +7% vs Gemini Flash on instruction-following (MAIR dataset) * $0.025/1M tokens, 150ms p90 latency at 100KB 🤗 We are open-sourcing the model weights, along with new challenging eval sets on @huggingface. Our Elo-inspired training methodology is already open-source! We're starting a series of technical deep dives to explain various failure modes zerank-2 fixes, with concrete prod examples, methodologies, and benchmarks. First technical deep dive in the comments.

@ZeroEntropy_AI (Nicholas Pipitone, @ghita__ha) will talk about how they used RLAIF to train their SOTA rerank model:

come chat about smarter search and smarter AI

next week will be extra @elastic-packed in SF monday meetup: luma.com/smart-search * @ghita__ha, @ZeroEntropy_AI: search tools for efficient AI agents * jesse, @fintool: LLMs and the next generation of financial search * @joshnkeezy, @reductoai: building a vision-first RAG pipeline with reducto and elasticsearch

The #1 bottleneck for software gen going forward is search / retrieval. Whether that’s open data sources (good web search) / personal data sources, it’s the layer that will become the biggest prereq to capturing value

@jeffreyhuber bullish on @ZeroEntropy_AI here

over 200 people have already RSVPd to join us along with the teams at @mastra and @mem0ai to talk about engineering context for Agents. RSVP: luma.com/rehr5jl2 @ZeroEntropy_AI

Join us with @mastra (TypeScript framework for Agents), @mem0ai (the long-term Agent memory layer), and @zeroentropy_ai(fastest and most accurate rerankers) on Oct 17th for our first Context Engineering Webinar! luma.com/rehr5jl2

most agents burn $$ reading 100 docs just to answer one question. a set up that works is @turbopuffer (fast, cheap, high recall hybrid search) with @zeroentropy_ai (fast, cheap, high precision reranker) tutorial + open benchmarks from the ZeroEntropy team zeroentropy.dev/articles/imple…

waking up to a team literally creating memes to show that @ZeroEntropy_AI is a "no-brainer" we want more memes please