Shoutout to OpenAI for allowing me to be so absurdly transparent about, well, everything.
Few companies have the balls to give early access to people like me. Even fewer do it with no strings attached.
I've been accused of being an OpenAI fanboy in the past. As silly as it may sound, I think this video shows why.
They listen. They learn. They improve. And most importantly: they've never once asked me to hold back.
They let me share how I really feel, and they take it to heart.
A lot of early access testers were unhappy with GPT-6.2 Astra. None of us were scared to say how we really felt.
The "negative" wave yesterday shows two things:
1. The model kinda sucks to use (sorry, it's true)
2. OpenAI does not restrict their EA testers in any way at all
Seriously. Mad respect to the team for taking this on the chin and letting us be so honest. It's not the norm, it means a lot to me. I hope y'all can take a second to appreciate it too :)
GPT-6.2 Astra is an incredibly capable model. Sadly, that's not enough anymore.
I did my best to show the good, bad and ugly parts of Astra in this video.
Whoever lead the "make it easier to work with" efforts for Gemini 4 Neon needs to be put in charge of Deepmind. jfc. They're so far ahead here it's insane.
Recent interview reveals why Zohran Mamdani prefers T3 Code over every other ADE.
"I take a step back and I think about what a New Yorker needs for a dignified life. A home they can afford. A bus that comes. And an ADE that opens before the bus does.
I have an old Lenovo. I put Linux on it. Claude helped me, of course. And I say this because T3 Code ran on that machine as hard and as fast as New Yorkers do.
I do not begrudge the big labs their desktop apps. What I am skeptical of is that with all that money they are still slower and worse to use. Our RAM, their reward.
Do I trust the labs? No. Do I trust the T3 team? Yes. Whether you are in Astoria, Allentown or Albuquerque, that is change you can feel in moving out of the terminal."
@joelcompiles Yep!
Thankfully it's a 3rd person game so the interframe compression is way cheaper and less loss-y.
I've had a conspiracy for awhile that Fortnite performed well on Twitch due to how much better it looks in nvenc vs a fast FPS like CoD or Halo
Sharing this diagram again because I need people to understand the difference here
Capability is the only thing you see on benchmarks, and it’s not even a complete picture of it
@dlrdbaker If my existing examples of Astra failing with basic prompts on OSS projects are not enough for you to create this data set, I don’t think you’re qualified to hill climb fixes for it.
Read this to the end, I promise it’s worth it.
Imagine that you’re ordering food at a restaurant.
You: “I’ll have the steak medium rare with fries”
Waiter: “What about the fries?”
You: “…huh?”
Waiter: “do you want the fries medium rare too?”
You: “idk what that means just cook them normal”
Waiter: “okay got it, coming right up!”
15 minutes pass, waiter comes back out
Waiter (panic’d): “hey man, we REALLY need to know if you want your fries cooked at 413 degrees or 471 degrees. Whole kitchen is held up until you decide!”
You: “wtf just do whatever the chef wants”
Waiter: “okay got it!”
30 minutes pass.
The waiter comes out with mostly passable fries, and an entirely burnt steak
You: “wtf happened this steak is burnt!”
Waiter: “so sorry, the chef got distracted when waiting for your answer about the fries. We can put the steak in the fridge to cool it off if you’d like?”
This is how it feels to use GPT-6.2 Astra.
@PatrickToulme I had one and really didn’t like it much. Hardware was cool but software didn’t really utilize screen well. We grinded hard to make t3 code a good experience on it tho.
Fold 8 and iPhone Duo are the ideal aspect ratio
"Thanks for opening up [those machines]...having a quiet bare-metal box without KVM steal will be huge for clean apples-to-apples comparisons"
Neon is so polite 🥺
It’s the end of 2026.
Anthropic recently released a model that’s changed how we code forever
Google put out a great general model that is pleasant to work with.
OpenAI put out the most intelligent model ever but it sucks to actually use.
It’s the end of 2025.
Anthropic recently released a model that’s changed how we code forever
OpenAI put out a great general model that is pleasant to work with.
Google puts out the most intelligent model ever but it sucks to actually use.