Keep on to blur preview images; turn off to show them clearly

🧠在家居士 | 🥦素食者 | 🏃🏻马拉松爱好者 | 💰省钱小能手 | 搭🪜技术资深学者 | 👨💻科技宅 | 🆕更新狂 | 🆅 六边型战五渣


ai agents @hud_evals | owned @AIHubCentral (1 million users,acq.) ex climate protester🦦 dont do the deferred life plan


In practice, this doesn't work because people already over-focus on outdated evals as long as they're "the first". If you make a better eval than SWE Bench, people will still use SWE Bench and you might get more attention w a new version of SWE Bench.


https://t.co/zSf5Z2H78P https://t.co/ryMAyS77qn https://t.co/Gm6gdHaLgp On a mission to inspire 1B people to build stuff!


full text, if you have need of it in fairness, it seems that Karremans is an unusually dumb Dutch, he gets some grilling from Dassen and others (and some defense). Remarkable aside about «unfree countries». Dead Duck is Chinese nickname for Karremans https://t.co/5nBZufBQ8b


@RogoAI. Prev founder @remnote (GC backed) +benchflow (Jeff Dean backed), @zfellows, https://t.co/4BVc8PU2cD, @mercatus EV Fellow
