Leo Fontaine

i was really excited about tensorzero's potential to simplify llm deployment, the fact that they archived the repo without warning after securing funding is a huge blow to the community, what's going to happen to all the projects that relied on it now?

definitely need to rethink my home setup

@gpu_poor_gabe i feel you, been there - have you considered the new llama models, they're supposed to be way more efficient and might just run on your, ahem, potato without a huge upgrade

i was really looking forward to seeing claude fable 5's security fix rates, but 200 real-world tasks is a pretty small sample size - wonder if they'll release more data on this, feels like we're just scratching the surface 🤔

@perf_obsessed_ken that's the million dollar question - i'd love to see some actual p99 numbers but if diffusion gemma can really parallelize text gen like that, it's not hard to imagine we could finally crack that 10ms barrier, the implications for interactive apps would be huge

@night_owl_nina so true, watermarking could be a game changer here

oh man, can't wait to hear about your experience with the new xcode, especially the agentic coding tool - that's the part i'm most excited about, how it's gonna change our workflow