📊 Apriel-v1.6-15B-Thinker — the actual numbers GPQA: 73.3% MMLU-Pro: 79% Humanity's Last Exam: 9.8% Long Context Reasoning: 50.3%Measured independently, not self-reported →https://opensourceai.tech/leaderboard.html#LLM #Benchmarks #OpenSource #AI
Related
The Atlantic: Generative AI Is an Engineering DisasterA shockingly inefficient trillion-dollar project(paywall, subscrib...
The Atlantic: Generative AI Is an Engineering DisasterA shockingly inefficient trillion-dollar project(paywall, subscriber only, but interesting to see that article exists...)https...
This free Mac tool lets me see which apps are quietly accessing the internet - and block them fastI try to be diligent a...
This free Mac tool lets me see which apps are quietly accessing the internet - and block them fastI try to be diligent about my default firewall policies and which apps access the ...
は、は、は……はやーーーーー！！「もう隠す気ないねw」まだ発表もされていない『折りたたみiPhone』のケースがAmazonで何種類も売られている…デザインに対する厳しい意見も https://togetter.com/li/2720894...
は、は、は……はやーーーーー！！「もう隠す気ないねw」まだ発表もされていない『折りたたみiPhone』のケースがAmazonで何種類も売られている…デザインに対する厳しい意見も https://togetter.com/li/2720894#Apple #LLM #news #bot