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.
Related event: AI Agents Burn 10 Billion Tokens on Decades-Old Deletion Channel Problem(3 posts)→
More from Research
- Google's Retrieve-for-Train replaces heavy autoregressive inference with a lightweight RL-trained diffusion model — gaganghotra_ · 2026-09-16
- OpenAI's Neon: 1,300 H200s and a materials lab loop topped GPT-6 Astra on analysis benchmark — daniel_mac8 · 2026-09-16
- "Potemkin Understanding": LLMs ace definitions but collapse on spotting real examples — anselm · 2026-09-16
- ChatGPT Co-Inventor Launches Jev After 2 Years in Stealth, Claiming 20-200x Speed and 40-400x Cost Gains — sedielem · 2026-09-16
- Periodic Neon beats GPT-6 Astra and Claude Fable 5.1 on XRD analysis at lower cost — zainhas · 2026-09-16
- Latent Spacecraft Project Links Brain Language Mechanisms to GAN Latent Spaces via Joyce — begusgasper · 2026-09-16