i've loved the autoforwarding feature in vscode since it came out (though, it's a bit slow)
love how other ssh clients are starting to add the same thing! will try this out
https://t.co/jhHvJRsCkv
Claude Code is running on a remote server, along with the web app it just built. Youโre on your phone.
You can still open localhost:3000 in Safari or Chrome.
Just create a local port forwarding rule in Termius and securely tunnel the remote port to your device.
No public ports. No extra setup.
๐Hy3 is here.
295B MoE. Best in its size class. Rivals trillion-scale flagships.
Reliable and affordable for most agentic usecases.
Apache 2.0. Friendly for commercial use.
FREE API for 2 weeks โ https://t.co/EyURKwTdgi
๐ค https://t.co/twqJpqb2SL
๐ https://t.co/4uEkIU1cW4
@bisheshab@JustinGorya i would say smarter models generally use more but if you have any data feel free to refute me here
all new sota/frontier models lately have been reasoning models, those reasoning tokens cost money. they think through the action more as they're a smarter model
@leodev if it does drop without gating i would assume anthropic is gonna extend the free fable period so people don't start moving to chatgpt
we'll see though
@RomanShalabanov@jun_song it's still decent though depending on the model you're using
you can get google ai pro for 18 months from g2a for $11, i paid less. includes storage too
https://t.co/21SUJb9zE6