{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2024-01-09-microsoft-pnnl-battery-electrolyte/","md":"https://postcutoff.com/e/2024-01-09-microsoft-pnnl-battery-electrolyte/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2024-01-09-microsoft-pnnl-battery-electrolyte","date":"2024-01-09","date_precision":"day","short_title":"Microsoft AI and PNNL screen 32 million candidates to find a solid electrolyte using ~70% less lithium","deck":null,"takeaway":"Microsoft's Azure Quantum Elements combined AI models and HPC to narrow 32 million inorganic candidates to 18 in about 80 hours.","category":"science","category_label":"Science & math","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":[{"n":1,"title":"Microsoft Azure blog: how Microsoft's AI screened over 32 million candidates to find a better battery","url":"https://azure.microsoft.com/en-us/blog/quantum/2024/01/09/unlocking-a-new-era-for-scientific-discovery-with-ai-how-microsofts-ai-screened-over-32-million-candidates-to-find-a-better-battery/","type":"official","group":"primary","domain":"azure.microsoft.com"},{"n":2,"title":"arXiv 2401.04070","url":"https://arxiv.org/abs/2401.04070","type":"paper","group":"primary","domain":"arxiv.org"},{"n":3,"title":"Chemistry World: Microsoft's AI system powers new battery discovery","url":"https://www.chemistryworld.com/research/microsofts-ai-and-high-performance-computing-system-powers-new-battery-discovery/4018731.article","type":"press","group":"press","domain":"chemistryworld.com"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Microsoft","Pacific Northwest National Laboratory"],"title":"Microsoft AI and PNNL screen 32 million candidates to find a solid electrolyte using ~70% less lithium","summary":"Microsoft's Azure Quantum Elements combined AI models and HPC to narrow 32 million inorganic candidates to 18 in about 80 hours. PNNL synthesised and tested the top pick, a Li–Na–Y chloride solid electrolyte reported to use about 70% less lithium, as a working prototype battery.","key_facts":["32M → 500k (stable) → 18 candidates in ~80 hours of screening","Synthesised and built into a prototype by PNNL","Prototype only; no commercial validation (arXiv 2401.04070)"],"key_numbers":[],"tags":["materials","batteries","hpc","screening"],"science":{"field":"materials","subfield":"battery materials","problem":"Reducing lithium content in solid-state battery electrolytes","result":"AI-screened new mixed Li/Na solid electrolyte synthesised and demonstrated in a prototype cell.","open_since":"","ai_system":["Azure Quantum Elements ML force fields and property models"],"human_role":"Human-led with AI tools; humans synthesised and tested","verification":{"key":"preprint","label":"Preprint only","text":"Lab-synthesised prototype; arXiv preprint"},"status":"confirmed","shock":""},"body_md":"## What happened\n\nA pipeline of ML property predictors filtered a huge chemical space in days, leaving a handful of candidates for chemists to make.\n\n## Why it matters\n\nIt is a concrete example of AI compressing the materials search funnel from years to weeks, though the result was a prototype rather than a product.","disputed":[],"related":[{"id":"2025-01-16-mattergen","url":"https://postcutoff.com/e/2025-01-16-mattergen/","date":"2025-01-16","date_precision":"day","short_title":"Microsoft's MatterGen generates materials to order","deck":"Flagship result later challenged as a known compound","takeaway":"Generative materials design is promising, but as with GNoME and A-Lab, \"new material\" claims need crystallographic scrutiny.","category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"disputed","labels":["Disputed"]},"sources":3,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Microsoft Research"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":null}