shipfeedAI news, curated daily

00:39:26 CET
21 MAY00:39:26shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

12/15/2023: Mixtral-Instruct beats Gemini Pro (and matches GPT3.5)

Mixtral-Instruct ranks alongside GPT-3.5 and above Gemini Pro on the LMSYS leaderboard, establishing the open-source model as a competitive option capable of running on consumer hardware.

Dec 15 · · primary fetch1 sourceupdated Dec 15 ·

Thanks to a karpathy shoutout, lmsys now has enough data to rank mixtral and gemini pro. The discussion highlights the impressive performance of these state-of-the-art open-source models that can run on laptops. In the openai Discord, users compared AI tools like perplexity and chatgpt's browsing tool, favoring Perplexity for its superior data gathering, pricing, and usage limits. Interest was shown in AI's ability to convert large code files with deepseek coder recommended.

Debates on privacy implications for AI advancement and challenges of running LLMs on local and cloud GPUs were prominent. Users reported issues with chatgpt including performance problems, loss of access to custom GPTs, and unauthorized access. Discussions also covered prompt engineering for large context windows and speculations about gpt-4.5 and gpt-4 future developments.

read full article on news.smol.ai
§ sources1 publication · timeline below
  1. news.smol.ai12/15/2023: Mixtral-Instruct beats Gemini Pro (and matches GPT3.5)primary