He called LLM math 'stupid' at 17 in 2023 — two years later he read the OpenAI results
fhuszar · x · 2026-10-10
Ferenc Huszár recalls a 2023 AI retreat where participants had LLMs tackle the Náboj high-school maths competition. A 17-year-old called it stupid: best published methods solved barely 60%, and only with ridiculous prompting schemes and majority voting. Two years later — after finishing high school and two years of undergrad — the same student read OpenAI's latest results, a striking illustration of how far LLM reasoning has come.
More from Models
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23
- Marker's lite mode scores 75.1 vs 42.3 for Azure Read on OmniParseBench — VikParuchuri · 2026-10-23
- Datalab launches lite OCR at $0.50 per 1,000 pages, 20-30x cheaper than Azure, Google and AWS layout APIs — VikParuchuri · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- PHP Foundation reveals Anthropic's Claude cyber model scanned PHP, validated with OpenAI's Daybreak Red — saibharadwaj · 2026-10-23