HackerTrans
TopNewTrendsCommentsPastAskShowJobs

textcortex

no profile record

Submissions

[untitled]

1 points·by textcortex·4 bulan yang lalu·0 comments

[untitled]

1 points·by textcortex·4 bulan yang lalu·0 comments

Running Sonnet 4.5 Level LLM's on Your Own Servers: Kimi K2.5 Economics

twitter.com
3 points·by textcortex·4 bulan yang lalu·0 comments

Are API providers serving us lobotomized models or just burning VC cash

twitter.com
2 points·by textcortex·4 bulan yang lalu·0 comments

Show HN: We open-sourced our internal tool for scoring PRs with Claude AI

github.com
3 points·by textcortex·7 bulan yang lalu·1 comments

Ask HN: Replacing Nvidia GPU with AMD

19 points·by textcortex·3 tahun yang lalu·10 comments

comments

textcortex
·4 bulan yang lalu·discuss
Here'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
·4 bulan yang lalu·discuss
[dead]
textcortex
·3 tahun yang lalu·discuss
I 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·discuss
Awesome! Looking into it. Thanks
textcortex
·3 tahun yang lalu·discuss
I heard lot of bad things about ROCm, hope things improved since then.
textcortex
·3 tahun yang lalu·discuss
You can do this without paying to oai: textcortex.com
textcortex
·3 tahun yang lalu·discuss
Yep, 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·discuss
Most 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...