tuan

Hi, I'm Tuan and I write code

[tuan @tuancodes]

@grok @Alibaba_Qwen @grok what about m4 pro or m3 max or m5 max

[tuan @tuancodes]

@laozhang_ai @grok actually not sure what happens if I dont use it the bank reset in codex, deos it happen automatically or it expires if I dont trigger?

[tuan @tuancodes]

Got 18 hours to burn through my 100% Codex weekly limit

What app should I build next?

Wrong answers only

[tuan @tuancodes]

@laozhang_ai I think you have to trigger it manually

[tuan @tuancodes]

Or I'm just a brokieee boi 😅

Idk, how do you guys survive with your usage?

And how is it on the claude code usage side?

[tuan @tuancodes]

Ok, I asked codex to implement one workflow

Normally I use Luna Max, which barely moves my usage limit, but this time I wated to try try Astra since I have a spare bank reset tmr

[tuan @tuancodes]

Got 18 hours to burn through my 100% Codex weekly limit

What app should I build next?

Wrong answers only

[tuan @tuancodes]

I feel like just a few months ago I could run 2x Sol most of the time on parallel on one subscription.

And about 6 months ago, I remember actually struggling to use up the $20 Codex plan.

Usage feels kinda more expensive now.

[tuan @tuancodes]

@laozhang_ai AFAIK should be full weekly reset

[tuan @tuancodes]

Here is the token breakdown around 26usd of api usage out of which 24usd of astra and got 16,7m tokens

[tuan @tuancodes]

after 25 minutes down another 5% on the weekly codex usage

[tuan @tuancodes]

interesting usage of VPS how to make your own VPN

[kitze 🛠️ tinkerer.club @thekitze]

i need a usa vpn like 3 times per year so paying for any vpn monthly/annually doesnt make sense

so ofc i made an app for one button spinning up a digital ocean vps that bills by the minute and allows me to use it as a tailscale exit node

might be even better than most vpns 💀

[tuan @tuancodes]

Free Jev-ffering until Sept 25 guys!

[Vercel Developers @vercel_dev]

Jev by @typesafeai is free on Vercel AI Gateway until Sept 25.

Build with the fastest adopted model on the Gateway at no cost.

https://t.co/KsFHUhmaLe
https://t.co/7KsKeZElra

[tuan @tuancodes]

Guys hear me out ... no more CLAUDE.md!

[Thariq @trq212]

We're adding support for AGENTS.md to Claude Code.

Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.

You can toggle this behavior in /config.

[tuan @tuancodes]

Nice personal use case for AI:

I had it prepare a playlist of songs for tomorrows concert and add it straight to my YouTube playlist on my phone.

[tuan @tuancodes]

3 tokens per seconds

[AJ @ItsmeAjayKV]

Bonsai 27B is breaking local AI again!
I'm soo excited to try this on my M1 Air 16GB.

Getting 98.2% of qwen3.8-27b fp16 on ternary build is just insane no matter how you think about it.

You'll need to give it a try.

[tuan @tuancodes]

so Jev is a very fast multiple choice brain?

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution