vivis dev

I don't understand the hype with TypeSafe's new Jev model. Despite having a different post-training method, they still fail in exactly the same way as LLMs (this example is from their eval suite). And we solved typesafe outputs in 2023, not sure why it's being touted as revolutionary.

Substack partners with Pangram to add AI text detection to all notes and posts. Unfortunately, creators can opt out and disable this for their content. Still a step in the right direction, and rebalances the scales back to the side of the reader. post.substack.com/p/against-cl...

LFM2.5-230M is a promising option for fine-tuning to translate natural language instructions into a series of tool calls. www.liquid.ai/blog/lfm2-5-...