Improving search ranking with chess Elo scores
Hello HN, I'm Ghita, co-founder of ZeroEntropy (YC W25). We build high accuracy search infrastructure for RAG and AI Agents. We just released two new state-of-the-art rerankers zerank-1, and zerank-1-small. One of them is fully open-source under Apache 2.0. We trained those models using a novel Elo score inspired pipeline which we describe in detail in the blog attached. In a nutshell, here is an outline of the training steps: * Collect soft preferences between pairs of documents using an ensemble of LLMs. * Fit an ELO-style rating system (Bradley-Terry) to turn pairwise comparisons into…
Improving search ranking with chess Elo scores launched on July 16, 2025 with 193 votes, #174 of 9,223 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
ZeroEntropy provides search infrastructure for retrieval-augmented generation and AI agents, offering two reranker models—zerank-1 and zerank-1-small—designed for high-accuracy document ranking. The company trained these models using a novel pipeline inspired by chess Elo scoring, which collects pairwise document comparisons via LLM ensembles and applies Bradley-Terry rating systems to generate relevance scores. One model is open-source under Apache 2.0, and both are available through an API and HuggingFace.
written from the facts on this page · September 2026
From the sources
ZeroEntropy provides state-of-the-art retrieval for developers building AI products.
ZeroEntropy trains small, specialized AI models — state-of-the-art rerankers, embeddings, and custom-trained models for production AI systems. Higher accuracy, lower latency, lower cost than the generalist alternatives.
ZeroEntropy's specialized models replace generalist alternatives with state-of-the-art accuracy. Better models in, better answers out. Teams switch to ZeroEntropy for the unmatched latency of our specialized models. Small, focused models run faster than the generalist alternatives — fast enough for real-time AI applications and agents at scale. zembed-1 outperforms leading embedding models even at lower dimensionality. zerank-2 is our state-of-the-art reranker. Get dramatically more accurate retrieval with one line of code. Fine-tune specialized models for your stack — query rewriting for enterprise APIs, context compression, and bespoke models for production agents. zerank-2 is our…from zeroentropy.dev
In the maker’s words, at launch
Hello HN, I'm Ghita, co-founder of ZeroEntropy (YC W25). We build high accuracy search infrastructure for RAG and AI Agents. We just released two new state-of-the-art rerankers zerank-1, and zerank-1-small. One of them is fully open-source under Apache 2.0. We trained those models using a novel Elo score inspired…
Does a similar job
all alternatives →
Real world (Jupyter notebook embed) way to assess data scientists2019 · hackerrank.com · ▲134
Sameshi – a ~1200 Elo chess engine that fits within 2KBFeb 2026 · github.com · ▲230I made a chess engine today, and made it fit within 2KB. I used a variant of MinMax called Negamax, with alpha beta pruning. For the board representation I have used a 120-cell "mailbox". I managed to squeeze in checkmate/stalemate in there, after trimming out some edge cases. I am a great fan of demoscene (computer art subculture) since middle school, and hence it was a ritual i had to perform. For estimating the Elo, I measured 240 automated games against Stockfish Elo levels (1320 to 1600) under fixed depth-5 and some constrained rules, using equal color distribution. Then converted…
A competition for small neural networks that play strategy gamesSep 2026 · tinybrains.dev · ▲116A ranked ladder for small neural networks that play strategy games. Train a model, write an adapter, upload two files, and get measured into a weight class from 8 KiB up.
A Implementation of Alpha Zero for Chess in MLX2025 · github.com · ▲71A chess engine implementation inspired by AlphaZero, using MLX for neural network computations and Monte Carlo Tree Search (MCTS) for move selection.
We built a better reranker and open sourced it2025 · huggingface.co · ▲6Hi HN, Our research team just released the best performing and most efficient reranker out there, and it's available now as an open weight model on HuggingFace. Reranker v2 was designed specifically for agentic RAG, supports instruction following (our v1 was the first to introduce this), and is multilingual. Along with this, we're also open source our eval set, which allows you to reproduce our benchmark results. By releasing these datasets, we are also advancing instruction-following reranking evaluation, where high-quality benchmarks are currently limited. Please give it a try and let us…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064Hey HN! Introducing Trickle Magic Canvas: the world’s first Agentic Canvas, where you can visually co-create apps and websites with AI, from idea to production. Why is a canvas better? Most AI tools today rely on linear chats or text prompts. We believe that limits creativity and clarity. Canvas changes the game. 1. Every version & page at a glance. Each page and sub-page lives on a timeline. You can quickly browse, edit, and preview progress like a living, visual document — no more digging through chat logs or scattered states. 2. The canvas is the context. Unlike linear chats, you can…
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
AI · 2025 · drawafish.com
Hi HN - I made a site that takes a UK postcode, grabs the local MP's information and generates an AI mockup of what their ID might look like. It's a small, silly protest at the stupidity of the Online Safety Act that just came into force. edit - My open AI credits got hugged to death, please use a known postcode (like one from Kier Starmer's constituency, WC2B6NH) in the meantime.
AI · 2025 · use-their-id.com