Running Sonnet 4.5 Level LLM's on Your Own Servers: Kimi K2.5 Economicstwitter.com3 points·by textcortex·il y a 4 mois·0 comments
Are API providers serving us lobotomized models or just burning VC cashtwitter.com2 points·by textcortex·il y a 4 mois·0 comments
Show HN: We open-sourced our internal tool for scoring PRs with Claude AIgithub.com3 points·by textcortex·il y a 7 mois·1 comments
Show HN: ICortex: LLM Powered Python Interpretergithub.com8 points·by textcortex·il y a 3 ans·0 comments
textcortex·il y a 4 mois·discussHere's how we use OpenClaw internally at TextCortex:→ Scans logs every night → Finds bugs before team wakes up → Reports root cause + evidence on Slack → Even knows who's already working on the fix
textcortex·il y a 3 ans·discussI would be interested in running inference on Instinct GPUs(MI250 with 128gb)BUT I can’t find any cloud provider to spin up a machine. It seems they are not yet available or cloud providers are not interested in supporting AMD hardware..
textcortex·il y a 3 ans·discussI heard lot of bad things about ROCm, hope things improved since then.
textcortex·il y a 3 ans·discussYep, agreed. Also somehow this AI 2.0 thing he is mentioning reminds me of web 3.0 bs. Baseless and delusional.
textcortex·il y a 3 ans·discussMost probably they are doing something called prompt tuning. This creates a small ai model that adds virtual tokens to prompt before passing to original model: https://developer.nvidia.com/blog/an-introduction-to-large-l...
textcortex·il y a 3 ans·discussWe released ICortex ai powered python interpreter half a year ago or so: https://github.com/textcortex/icortex
textcortex·il y a 3 ans·discussWe released an LLM powered python interpreter namely ICortex as an open source project back in 2022: https://github.com/textcortex/icortex
→ Scans logs every night → Finds bugs before team wakes up → Reports root cause + evidence on Slack → Even knows who's already working on the fix