LeCun says he 'brought a proof': JEPA world models can match LLMs with far less memory
ylecun · x · 2026-11-04
Yann LeCun shared a paper arguing LLMs accumulate declarative knowledge, which is why they need huge parameter counts and memory. JEPA world models replace knowledge accumulation with understanding: with anti-collapse criteria like SIGReg or VCReg, the underlying similarity structure of the data uniquely determines the representation point cloud's shape. That lets JEPA-style models be useful with considerably less memory and training data than LLMs. A PhD trained in Vapnik's kernel-methods school says the proof changed his mind about LeCun's approach.
More from AGI Musings
- Ramez Naam: power concentration is the biggest AI risk, plural AI makes us safer — sebkrier · 2026-11-04
- Sequoia summit: the diffusion gap between model progress and enterprise adoption is the opportunity — FinanceYF5 · 2026-11-04
- Sequoia summit: ease of use is underrated; build around customers, not model releases — FinanceYF5 · 2026-11-04
- Sequoia's advice to AI founders: chase customers, not model launches — FinanceYF5 · 2026-11-04
- Sequoia: AI shifts competition from systems of record to selling outcomes — FinanceYF5 · 2026-11-04
- Sequoia: next-gen AI apps must deliver 10-40x gains, not 10-40% — FinanceYF5 · 2026-11-04