{"schemaVersion":"1.0","generatedFrom":"https://brightaifuture.com/discoveries/fusion","record":{"id":"fusion","headline":"Holding a plasma in shape.","canonicalUrl":"https://brightaifuture.com/discoveries/fusion","datePublished":"2026-09-05","dateModified":null,"sourcePublicationDate":"2022-02-16","author":null,"publisher":{"name":"Bright AI Future","url":"https://brightaifuture.com/"},"topics":[],"summary":"Researchers used reinforcement learning to control magnetic confinement in a research tokamak.","evidenceState":"Demonstrated","keyFacts":[{"label":"AI’s role","value":"A trained policy commanded the tokamak’s magnetic coils."},{"label":"Documented result","value":"The controller demonstrated multiple plasma configurations on TCV."},{"label":"Important limitation","value":"Plasma control is not net energy production or commercial fusion."}],"limitations":["Plasma control is not net energy production or commercial fusion."],"evidenceLinks":[{"title":"Magnetic control of tokamak plasmas through deep reinforcement learning","url":"https://www.nature.com/articles/s41586-021-04301-9","type":"paper"}],"evidencePackUrl":"https://brightaifuture.com/evidence-pack/fusion","embedUrl":"https://brightaifuture.com/embed/story/fusion","attribution":{"credit":"Bright AI Future","requirements":["Link to the canonical Bright record.","Keep material limitations with the claim they qualify.","Link to the original evidence when repeating a substantive claim.","Do not describe a source check or organization-reported result as independent verification."],"sourceRights":"Linked source material, quotations, trademarks and media remain subject to their owners’ terms. No reuse right is granted for third-party media."}},"claim":{"humanProblem":"Hot plasma must be controlled within a complex magnetic system.","priorConstraint":"Controllers require specialized engineering for target configurations.","aiRole":"A trained policy commanded the tokamak’s magnetic coils.","documentedResult":"The controller demonstrated multiple plasma configurations on TCV.","whyItMayMatter":"A tool for researchers exploring fusion reactor designs.","unresolvedQuestions":["Test broader conditions and more demanding devices."]},"evidenceAssessment":{"state":"Demonstrated","claimConfidence":"unassessed","reviewState":"source-checked","reviewMethod":null,"reviewNote":"Legacy source check; no named human reviewer is recorded in this projection.","lastSourceReview":"2026-09-05","independentVerification":"not-established-by-this-source-review"},"sources":[{"id":"source:fusion","title":"Magnetic control of tokamak plasmas through deep reinforcement learning","url":"https://www.nature.com/articles/s41586-021-04301-9","type":"paper"}],"revisions":[],"corrections":[]}