Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then.
Recommended
Advancing content provenance for a safer, more transparent AI ecosystemOpenai Operation "Doppelganger": Russian influence activity targeting UkraineOpenai Everyday work with ChatGPT WorkOpenai Romance scams: AI-enabled romance scam workflowsOpenai Will Hurd joins OpenAI’s board of directorsOpenai Statement from the OpenAI Board of Directors on the Nonprofit Commission ReportOpenai
Trained on 100,000+ Voices: Deepgram Unveils Next-Gen Speaker Diarization and Language DetectionDeepgram
Money! Money! Money!Redis
Ringing in the New Year with a New Office in LondonRedis
Let’s Play Master and Servant: Real Time Synchronization Tool for Redis MigrationRedis
How a marketing agency increased client conversions 35% with Zapier CanvasZapier
How to implement AI training for employeesZapier
WooCommerce: App spotlightZapier
6 ways to use the Zapier Zoho CRM integrationZapier
Plumsail Documents: Zapier spp spotlightZapier
Looping by Zapier: Repeat actions for itemsZapier
OData or GraphQL? The Best Tech for Developing an API Is Neither or Both!Thenewstack
Product updates: Rollbacks, batching, sandbox tunnels & moreModal
How Hunch supercharged AI workflows with Modal SandboxesModal
Product updates: Datadog integration, lower function latency & moreModal
