Behrad Khodayar

@fabrice_mayrand skeptics in comments just don't understand how big this pie can be.

This is insane Cheaper Inference is selling API access to most major models for 30% off. Use OpenAI, Anthropic, and Google models through a drop-in OpenAI-compatible API. No contract, no migration required.

@filip_hric x.com/behradkhodayar…

OMG WHAT IS HAPPENING?!

what an INSANE goal 🏴󠁧󠁢󠁥󠁮󠁧󠁿🇦🇷

@paw_lean The point is Argentina is running full "thinking mode": lots of waiting, back w best outcome. hard to beat.

This was the first time I really got into football, so I’m so gutted 😭 But it’s also… Argentina. Goat team!

🏴󠁧󠁢󠁥󠁮󠁧󠁿🏴󠁧󠁢󠁥󠁮󠁧󠁿🏴󠁧󠁢󠁥󠁮󠁧󠁿 Been listening to Wonderwall all day today

Argentina playing in "thinking mode": Lots of waiting, but back w/ best results.

Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched? Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens! switch-to-codex.openai.chatgpt.site

Claude Code is fine, but configuring a fully working environment to extract best out of it takes time, I mean providing the required rules, skills, sub-agent configurations, etc... to an extent that I had recently created a boilerplate starter template for my day to day stack of Python,TS,PSQL,Docker (available on my GH). Codex as my frens say requires much less configurations. Looking forward to giving it a ride.

@antirez Lol, same here, but I managed to solve all my life's problems w/ Fable.

I was burning all my Fable tokens like Cartman in Casa Bonita since 7th of July was the last day and then...

@zephyr_z9 Meta fading out. "This year" is a decade & not even targeting Mythos.

No Mythos from Meta

@sama wen shutdown then?

GPT-5.6 sol launches thursday! happy building

@NickSzabo4 remember ur concerns? Ppl r literally "thanking" Meta for this now! The problem is users value convenience waaaaay more than privacy.

I don't get this level of insanity

Personalized education & testing is such an obvious yet complex problem to solve at this point (No leetcode while v have fable and glm 5.2 plz) Billions of dollars in grabs

Components of a coding agent: a little write-up on the building blocks behind coding agents, from repo context and tool use to memory and delegation. Link: magazine.sebastianraschka.com/p/components-o…

A super long overdue (3+ years?) post on scaling laws. Compute is expensive. Scaling laws are a way to help us reason about the optimal compute allocation between data and model size before committing to a large run. The post covers what scaling laws predict, how compute-optimal allocation works, why Kaplan et al. and Chinchilla disagree, and how data limits + fitting details make extrapolation tricky. lilianweng.github.io/posts/2026-06-…

After building a few fullstack (Python/FastAPI + React + PostgreSQL) apps, I've refactored (& continue to make it better) a full-stack Claude Code template, which improves it's performance (basically to a teammate, not an afterthought). Go: 1- clone as template 2- put ur project context in CLAUDE.md 3- & u're good to go. start shipping: 👇

👀👀

@mardehaym Seems they need a smarter model to stop 'em from doing this. everybody's lost their mind smh

POV: your team's 24 hour bill after using Fable 5. Stop using the best models. They are uneconomical.

@ivanfioravanti Throw the phone away man! do digital detox.

This morning towards rifugio Bertone.

@scaling01 & generate a new one so the new generation of models solve them

I now expect every new generation of models to solve a previously unsolved problem