Running Sonnet 4.5 Level LLM's on Your Own Servers: Kimi K2.5 Economicstwitter.com3 points·by textcortex·4 bulan yang lalu·0 comments
Are API providers serving us lobotomized models or just burning VC cashtwitter.com2 points·by textcortex·4 bulan yang lalu·0 comments
Show HN: We open-sourced our internal tool for scoring PRs with Claude AIgithub.com3 points·by textcortex·7 bulan yang lalu·1 comments
textcortex·4 bulan yang lalu·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·3 tahun yang lalu·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·3 tahun yang lalu·discussI heard lot of bad things about ROCm, hope things improved since then.
textcortex·3 tahun yang lalu·discussYep, agreed. Also somehow this AI 2.0 thing he is mentioning reminds me of web 3.0 bs. Baseless and delusional.
textcortex·3 tahun yang lalu·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...
→ 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