It’s wild how differently Codex and Claude Code feel.
Codex is a Stanford engineer: you give it the shape of an idea and it comes back in 5 minutes with a working prototype but with code that feels like it was written 5 red bulls deep at 4 am.
Claude Code is spiritually Eastern European: demands an annoying amount of clarification, goes on vacation for a couple of months, but then delivers something elegant enough to make Knuth cry.
Anthropic has to add a bunch of features because their public models haven’t improved since December
Codex has gotten 10x better since and it’s largely the models.
Also - Codex is far ahead on a lot of “end to end” stuff. Computer use, goals, remote control, all the things that actually make me more productive.
Claude Code has better features to tweet about. Codex is quietly becoming the best solution for actually writing software.
for just $70, you can:
- go to Stanford
- buy this hoodie
- claim you "went to Stanford, but left before graduating"
- all of which is technically true
- wear this to the VC pitch meeting
- say words like "agentic workflows" and "non-consensus consensus trends"
- raise a $10m seed round
- spend it all on tokens and shut down in 1.5 months
but most stop at step 1 (they don't want to drive that far)
Great read. Computer literacy classes should become mandatory in schools around the world.
And even that is not enough... We need parents, mentors and educators to all step in here
Before it’s obvious.
Before it’s proven.
Before it’s consensus.
Someone believes first.
At FRV, that’s where we show up. Working closely to where innovation begins, seeing the potential before others and having the conviction to act before there is proof.
#FirstBeliever
Let me local AI pill you:
1. It sucks compared to SOTA
2. It can’t code so well
3. It can be a good agent
4. It can be great at chat
5. It can be fine as a researcher
6. It can be a great automation engine
7. It can be tuned however you want
8. It teaches you how the sausage is made
9. It works on a plane, or in an outage
10. It costs your electric bill + hardware
11. It is better than the AI we gave up coding for a year or 2 ago.
Local AI is self defence, it is a go kit, it is a rebalancing of power.
It’s delusional to think it approaches or will ever approach SOTA, the scale of private labs blows anything you can get for less than 25k USD out the water.
Local AI is a bet that prices won’t stay this low, that private corporations with closed source weights can’t be trusted to stay consistent.
I am more than happy to rent a Ferrari for dirt cheap, but i should also have a beater Toyota if I can afford it.
Local AI is the car I can depend on to be there tomorrow, something that’s mine.
📢 ONLYOFFICE Docs Home Server #Giveaway 🎉
To celebrate the release of #ONLYOFFICE Docs 9.3, we’re giving away 3 Home Servers 🏠💻
📅 Feb 26 - Mar 1 (inclusive)
🔁 Retweet to enter
🎯 Winners chosen randomly & announced next week
Good luck! 🍀
@chrislevan You can try out @opencode (open source Claude code, but better). They even have a few free models to try out that work better that Opus for UI/UX (GLM-4.7 and especially MiniMax M2.1).
@vaxryy I don't like seeing the error messages when I log in (in the couple seconds before the plugins load). Also since the main plugins that interest me are layout related ones, when they break it makes hyprland unusable
@Melavin@MKBHD Works fine on pixel (I have the 6 and use Niagara). I think this used to be a bit buggy, but I've never had issues on any of my devices.