LLM | doing the math for you

Recursive Language Models: when “more context” stops meaning “more tokens”

—

by

Recursive Language Models fix context rot by treating long prompts as external state—let models orchestrate, not ingest all context.

—

by

AI reconstructs mathematics: language models autonomously rediscover proofs, conjectures, and reshape how we do math.

—

by

LLM safety limits: prompt filters can be bypassed by adversarial encodings; defense-in-depth, monitoring, and layered controls needed.

—

by

OpenAI trains LLMs to self-report missteps via ‘confessions’, improving honesty and safety with minimal performance cost.

—

by

Self-evolving agents: off-the-shelf models bootstrap via Python REPL and curriculum to dramatically improve math, coding, and reasoning.