TLDR Tech / AI
Recent OpenAI research has demonstrated the ability of LLMs to solve frontier problems in mathematics
Researchers set out to find out how good frontier LLMs are at doing frontier theory research. They designed a prover-verifier workflow that used GPT-5.5 Pro as the solver and Claude Opus 4.7 as the verifier. This workflow was stress-tested on open problems from areas with very different levels of familiarity. The results were surprisingly strong and the system resolved a list of open questions.
Read the full story