Aivan Monceller

I share interesting things I find, what I’m learning, and projects I’m trying. Follow me if you like tech, creative stuff, and learning new things. INFJ-T

[Aivan Monceller @aivandroid]

Created a video how to train Flux LoRAs using my convenience script utilizing ai-toolkit on @quickpodio

https://t.co/MvqYVjdVkm

[Aivan Monceller @aivandroid]

Glad to know that we now have better options in Bedrock.

[Amazon Web Services @awscloud]

Now generally available, @OpenAI GPT-5.5, GPT-5.4, and Codex on Amazon Bedrock.

Deploy frontier AI models with automatic scaling through Bedrock's next-gen inference engine.

With these offerings on Bedrock, customers can:
◽ Build autonomous agents that handle multi-step coding, data analysis, and knowledge work with GPT-5.5 and GPT-5.4
◽ Bring Codex, the OpenAI coding agent, into your dev workflow and route all model calls through Bedrock. Pay per token, scale as you go.

[Aivan Monceller @aivandroid]

@cjzafir How is Deepseek v4 on long running goals?

[Aivan Monceller @aivandroid]

@reach_vb Is gpt web search supported on bedrock? That would make a difference vs anthropic models on bedrock.

[Aivan Monceller @aivandroid]

@kohya_tech @bdsqlsz congratulations you deserve it a lot

[Aivan Monceller @aivandroid]

And "there will be more"
https://t.co/7MnCzal9kS

[Tibo @thsottiaux]

@argofowl There will be more

[Aivan Monceller @aivandroid]

The USD $100 Codex plan was honestly very worth it this month.

The 5x to 10x Codex usage boost already made it feel generous, then the limits got reset 4 times too lol.

That basically meant I could leave Codex /goal running for long stretches on my personal projects without constantly thinking, "am I about to hit the limit again?"

At this point I am half treating the reset generosity as a Codex feature that you can't find elsewhere. Thanks @thsottiaux

This is why I love Codex.

[Cline @cline]

Anthropic's new Opus 4.8 scores 3.6% lower than GPT 5.5 on Terminal-Bench 2.1. Available to compare side-by-side in Cline now.

(They also announced a plan to release new models with higher intelligence than Opus after adding stronger cyber safeguards in the coming weeks.)

[Aivan Monceller @aivandroid]

@thsottiaux Please release a 10x plan , between Pro Lite and Pro Max .. ChatGPT said you can call it Pro Core

[Aivan Monceller @aivandroid]

@Youssofal_ Hints on how you modified the binary?

[Tyler @rezoundous]

Now, I'd rather wait for Codex / Claude limits to refresh than to code myself.

It's bad, guys.

[Aivan Monceller @aivandroid]

@Dimillian Use it on windows

[Aivan Monceller @aivandroid]

@ellev3n11 A sub for composer inference

[sunil pai @threepointone]

remember when programming was free

[Aivan Monceller @aivandroid]

A surprising number of brilliant people I know have gone through a C# chapter

[Luke Parker @LukeParkerDev]

did you know the entire opencode team used to do C#?

much to think about

[Aivan Monceller @aivandroid]

@LukeParkerDev I love C#

[Aivan Monceller @aivandroid]

@kohya_tech I wonder if there is a difference in result typing english vs japanese

[Aivan Monceller @aivandroid]

@kohya_tech That's Codex for you , I wish I have that VRAM though..

[Aivan Monceller @aivandroid]

@OpenAI I'm stuck on "Waiting for desktop..." on Windows, is this supported on Windows?

[Melvin Vivas @DonvitoAI]

Free $60 for new accounts in @DevinAI

Thanks @cognition

Giving it a spin today

[Aivan Monceller @aivandroid]

multiplexing over SSH used to be a game of "which keybinding will break my scrollback today?"

@Zellij_dev Zellij is the first tool that actually feels native over a remote connection.

no more ctrl+b + [ just to see a log.

web sessions that don't lag.

layouts that don't explode.

the "old way" just became obsolete.