[Thread] A new US paper shows the best frontier LLM models achieve 0% on hard real-life Programming Contest problems, domains where expert humans still excel — This is really BAD news of LLM's coding skill. ☹️ The best Frontier LLM models achieve 0% on hard real-life Programming Contest problems, domains where expert humans still excel. LiveCodeBench Pro, a benchmark composed of problems from Codeforces, ICPC, and IOI ("International [image]
Tuesday, June 17, 2025
[Thread] A new US paper shows the best frontier LLM models achieve 0% on hard real-life Programming Contest problems, domains where expert humans still excel (Rohan Paul/@rohanpaul_ai)
Subscribe to:
Post Comments (Atom)
Once hailed as an AI visionary, Satya Nadella faces pressure as a compute crunch forces Microsoft to prioritize its own AI products over Azure cloud customers (Ashley Stewart/Business Insider)
Ashley Stewart / Business Insider : Once hailed as an AI visionary, Satya Nadella faces pressure as a compute crunch forces Microsoft to ...
-
Sohee Kim / Bloomberg : South Korean authorities are investigating a data leak at e-commerce giant Coupang that exposed ~33.7M accounts; ...
-
Top fintech companies are rushing to tap into this new consumer trend, with several of them offering digital solutions to small merchants. h...
No comments:
Post a Comment