AI agents burned 10B+ tokens on a deletion channel problem open since the 1960s
DimitrisPapail · x · 2026-09-16
Researcher Dimitris Papail recounts setting AI agents loose on the capacity of the deletion channel, a problem open since the 1960s.
- The agents consumed over 10 billion tokens mixing old and new approaches, but did not fully resolve the problem.
- His takeaway: reality has no obligation to fit the kind of paper we'd most enjoy reading — some problems demand an unappealing patchwork of arguments plus the brute force of a thousand GPU hammers.
- A rare first-hand experiment on whether AI agents can do genuinely open-ended mathematical research.
More from Research
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Mistral Large 4 writes a quantum chemistry SCF solver from scratch with one short prompt — MistralAI · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- New theory paper proves linear decay is the unique minimax-optimal stepsize schedule for SGD — konstmish · 2026-11-02
- Karpathy's nanochat: the best ChatGPT $100 can buy, near 60k GitHub stars — karpathy · 2026-11-02
- After reading 46 resources on agent evals, one author explains why her 95% score was misleading — blaizedsouza · 2026-11-02