Four weeks and 10B tokens: AI agents take a crack at the 1960s deletion channel problem
DimitrisPapail · x · 2026-09-17
Dimitris Papail published a long-form account of tasking AI agents with the deletion channel capacity problem, open since the 1960s.
- Roughly four weeks of GPU time and over 10 billion tokens, mixing classic literature with agent reasoning
- The agents did not resolve the problem, but the write-up offers a candid case study of agentic research and where current models stall
- He argues the failure itself is informative, mapping the gap between hype and actual open-math capability
The article is being shared as a rare first-hand log of AI's real level in scientific research.
More from AGI Musings
- Polymarket puts 36% odds on frontier AI labs agreeing to pace AI by 2026 — Polymarket · 2026-09-17
- A Private WoW Server Would Be the Perfect Sandbox for Testing AI General Intelligence — djcows · 2026-09-17
- A 2008 Story Description Now Reads Like LLM Output: 'Semantic Apocalypse' — erikphoel · 2026-09-17
- OpenAI cracks a math logjam as 25 Fields medalists sign cautionary letter — nordicinst · 2026-09-17
- 'By 2030' AI safety assurances don't reassure, commentator notes — FlorianGallwitz · 2026-09-17
- Nate Silver voices skepticism on RSI, spars with AI class-action plaintiff — dhadfieldmenell · 2026-09-17