incredibly clever chunking trick by the zeroentropy team (now at notion)
llms are autoregressive, which means generating text is super slow.
but passing text in and finding the logprobs of a particular token at all locations takes a single forward pass!
so we can ask the llm, 'like yo llm, please chunk this by putting this unlikely character 段 wherever there should be chunks"
and we instantly get the segmentation locations (well, not instant, we still need a forward pass which means we need to prefill)
but the advantage is super accurate chunks in the time it takes to prefill!
Excited to welcome @ZeroEntropy_AI to @NotionHQ.
The future of AI products will not be powered by a single model, but by intelligently matching each workload with the best combination of quality, speed, and cost. This is an important step in that direction.
https://t.co/2PzbYD3Z9p
Excited to share that the awesome @ZeroEntropy_AI
team joined @NotionHQ
We have already been collaborating for a long time. now we are working even closer. Anyone who can make search ranking 85% faster is a happy addition to the Notion team :)
We're excited to announce that @NotionHQ has acquired ZeroEntropy.
We first got to know the Notion team as one of our top customers: Notion AI has been running on our reranker zerank-2, replacing models from larger, better-funded competitors with an 85% latency improvement. Now our whole team is joining Notion to keep building.
Alongside the acquisition:
🔓 All of our models are now open source under Apache 2.0 on @huggingface , run them through any inference provider, no commercial license required.
📅 All ZeroEntropy products remain fully supported until September 4th, 2026, after which they will be sunset.
Our migration guide covers every path, and our team is available on Slack, Discord, and email to help every customer transition.
Full story on our blog and migration guide below.
Thank you to our customers, investors, and partners for believing in ZeroEntropy.
It's been a privilege to serve you, and we can't wait to keep building things you love at Notion.
Is Matryoshka dead?
Every frontier embedding model uses MRL.
But we tested it across a full hyperparameter sweep and it's lossy at every dimension.
A small projection matrix trained on top of zembed-1 beats MRL across the board. Including at full dim.
Results:
zembed-1 @ 160 dims > OpenAI @ 1536 dims
zembed-1 (no MRL) > voyage-4 (MRL)
@ZeroEntropy_AI
Super excited to share that @ZeroEntropy_AI is now a provider in the @vercel AI SDK
If you're already building with `ai`, our models are one import away.
→ zerank-2 for reranking
→ zembed-1 for embeddings
→ more models to come 👀
Happy shipping!
The excellent zerank-2 reranker model by @ZeroEntropy_AI is now fully compatible with Sentence Transformers, no `trust_remote_code=True` needed.
It's 4B and cc-by-nc-4.0, and performs very well.
I'm quite fond of their training methodology, I'll explain in the 🧵
On Gemini Flash 3.5 pricing
Prices for mini/Flash models have been dramatically increasing with every release
4x increase on input and more than 8x on output between Gemini 1.5 Flash and Gemini 2.5 Flash
And now another 3x increase
The world needs more cost efficient, lightweight models to run at the scales needed, especially for task specific workflows that don't need frontier models
Token efficiency and intelligence compression are what's needed
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!
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!