GPT-6 could use 2-5x pre-training compute for RL, speculates scaling01
scaling01 · x · 2026-09-07
AI commentator scaling01 argues that continuous 100-day pre-training runs are obsolete since they waste algorithmic progress, and floats a base-case guess for GPT-6 ("Astra"): on top of pre-training, roughly 2x-5x the pre-training compute spent on RL. Pure speculation, not confirmed.
Related event: KOL Tests Astra, Sees No AGI; Speculates GPT-6 Uses Up to 5x Compute(3 posts)→
More from Models
- User: Opus 4.8 nails UI work while OpenAI lacks focus for everyday coding needs — aloncarmel · 2026-09-07
- Netherlands builds 'Dutch AI' by finetuning Qwen 3.5 27B in subsidized datacenter — teortaxesTex · 2026-09-07
- Abacus.AI CEO: DeepSeek Handles 80% of Everyday Tasks at 100x Lower Cost — bindureddy · 2026-09-07
- Users Report Day-One Bans Over 'Distilling' as Opaque Moderation Draws Fire — QuixiAI · 2026-09-07
- Naval's bike analogy for SFT vs RL explains why DeepSeek R1 shocked the industry — McDonaghMatthew · 2026-09-07
- DeepSeek-R1 grew reasoning with pure RL, no SFT — and that's what changed everything — McDonaghMatthew · 2026-09-07