Codeforces

Researchers demonstrated that hidden reasoning blocks in LLM APIs from Google, OpenAI, and Anthropic can be extracted via a replay attack, achieving near-perfect recovery of up to 12,000 tokens. The a…

Researchers introduced a controlled student-teacher protocol to study when natural-language feedback improves multi-turn language agent performance beyond repeated attempts. Testing thirteen open-weig…

The developer of dailyprog, a daily coding puzzle site, built an LLM-based puzzle generator to automate content creation after manual puzzles proved unscalable. The generator uses a structured vocabul…