cmdtab
Joined 1 year ago
Joined 1 year ago
Even the smallest models are RL trained to use shell commands perfectly. Gemini 3 flash performs better with a cli with 20 commands vs 20+ tools in my testing.
cli also works well in terms of maintaining KV cache (changing tools mid say to improve model performance suffers from kv cache vs cli —help command only showing manual for specific command in append only fashion)
Writing your tools as unix like cli also has a nice benefit of model being able to pipe multiple commands together. In the case of browser, i wrote mini-browser which frontier models use much better than explicit tools to control browser because they can compose a giant command sequence to one shot task.
Made the mistake. Never again.
Fly, railway, render. Avoid. All have weird show stopper bugs for any reasonable scale and you will fight against the platform compared to using big cloud.
And big cloud works better even in cases where PAAS is advertised as simpler (google cloud run and build is as easy to setup as railway but you have much more knobs to control traffic, routing, roll out etc)
https://runable.com is an AI suite for everyone. You can create decks, reports, documents, designs, websites etc by just describing what you want.
We are looking for exceptional engineers to join us as we scale. We already process 100 billion+ tokens and billions of requests monthly.
Send your best work to [email protected]
We don’t do DSA, leetcode etc and have a very hands on approach to interviewing
Welcome to the internet
Runable is a general purpose AI agent for any task you can think of. You can create presentations, websites, docs, reports, videos, images, use over 3000+ services, control remote browsers, etc.
I’m looking for savvy people with potential to grow quickly who wants to work at a startup. If you want to take ownership, learn and be a founder in future. This is the place for you.
Shoot me an email with your github or portfolio: [email protected]
Lot of issues with slow AWS provision or missing APIs on AWS side so it would take hours to delete resources created by them.
[email protected]