Exa launches Snapshot: 400B historical webpage snapshots for time-travel search
ycombinator · x · 2026-09-18
Exa has introduced Snapshot, an index of 400 billion historical webpage snapshots that lets you or your agent search the web as if in the past and diff pages over time.
Unlike date filters—which leak present content into past results since pages keep updating—Snapshot pins webpages to their historical state. Use cases cited include backtesting trading models without data leakage (e.g. would a model using March 2025 web data have predicted Anthropic's growth), keeping time constant for RL training runs, and exploring the pre-AI web.
Related event: Exa Launches Snapshot: 400 Billion Historical Web Pages Searchable(3 posts)→
More from coding & agent
- Dev builds 3D universe explorer with 20 galaxies, 767 planets using Codex GPT-6.1 Sol — OpenAIDevs · 2026-11-02
- ChatGPT, Claude and Perplexity's fetchers don't run JavaScript, leaving client-rendered sites invisible to AI — gaganghotra_ · 2026-11-02
- SGLang boosts multimodal inference >10% by replacing GPU memory bookkeeping with a dict lookup — charles_irl · 2026-11-02
- kivi: hold Fn, talk, and it types polished text anywhere on your Mac — itsOmSarraf_ · 2026-11-02
- A base LLM plus 11 lines of code is all you need for a decision model — helloiamleonie · 2026-11-02
- Fix codebase structure before asking AI agents to write tests, says engineer — arpit_bhayani · 2026-11-02