Pinned Tweet
We'll see if I just threw away money on premium+ again. My old account was banned/censored by this "free speech" platform b/c I was upsetting too many Jew haters and Hamas supporters.
Truth Gone retweeted
I used Gemini 4 Argon to make Subway Surfers for the new flying Tesla Roadster 🚀
Fly over moving traffic, hit the thrusters to barrel roll in the sky, and collect air power-ups to set a high score.
Play + code below!
I think I might try to. I use Codex and Claude Code. I like Codex to control Claude Code, but maybe I'm going to start. Maybe I'll flip-flop and use Claude as my main agent if Codex can't get it back together.
Codex and Tibo have officially run out of ideas for the 28 days of shipping.
Expect to see a ton of resets before Astra 6.1 deploys.
Ironically Claude code has been shipping much more and the new desktop app is dialed.
I’m not sure what’s going on at OpenAI but they are currently being lapped by Anthropic.
Truth Gone retweeted
🚨 ChatGPT desktop users beware: A bug may be causing unnecessary wear on your SSD. @OpenAI
I noticed constant SSD activity whenever the app was running. Tracing the writes revealed that the animated desktop Pet was triggering a rewrite of the entire ~1 MB app state file AND its backup, about 10 times per second.
That amounted to 385 MB of file writes in 20 seconds, just to persist changes to the Pet’s position.
Setting Pet to “None” stopped the activity immediately.
If you leave the app running all day, check this setting!
Truth Gone retweeted
I love Codex and rely on it for professional and personal work. I need dependable organization, phone sync, and scheduled tasks that keep running. Here’s what keeps breaking—and what I’m asking @OpenAI @OpenAIDevs to fix.
You can pretty much reverse engineer any device in your home and build a mac app around it. Applied to lights, doors, ac and even the future robot helper.
Here's the skill: github.com/morluto/rea
It's crazy what you can build nowadays with a skill and a few prompts.
Truth Gone retweeted
Self-improving agents just got a strong open-source option.
Hermes Agent runs locally, builds its own skills over time, and supports 300+ models. It has persistent memory and sandboxed execution.
github.com/NousResearch/herm…
Truth Gone retweeted
My favorite people are the ones confidently declaring AI a bubble while admitting they’ve barely used anything beyond the free version of ChatGPT.
Imagine reviewing the entire automobile industry after sitting in a golf cart.
That’s the level of expertise we’re dealing with.
If everyone using Codex isn't having these problems, then I don't know if they're using Codex properly…..
I love Codex and rely on it for professional and personal work. I need dependable organization, phone sync, and scheduled tasks that keep running. Here’s what keeps breaking—and what I’m asking @OpenAI @OpenAIDevs to fix.
Truth Gone retweeted
🚨 Is OpenAI losing control of the Codex situation?
Users are fed up with usage limits and ongoing issues.
Tibo keeps sharing updates, but what’s happening behind the scenes?
Is OpenAI scrambling to fix Codex or preparing a new model to challenge Opus?
What’s OpenAI prioritizing right now?
Openai accidentally (again) fell into the trap of over-building
they recognized they had the lead, codex felt polished enough and they just got their hands on Astra
so then they decided to push a bunch of products forward, thinking that with the power of astra they will be ready for release
what we have seen is most of them not actually ready for release. right idea, bad execution
based on my experience with astra, openai's recent products/features actually correlates quite well with what the model is like to code, gets the general idea but leaves behind a bunch of inefficiencies and polish but makes you think its ready
this is just me trying to connect the dots, i recognise i dont have all the context
OpenAI seems to be struggling to keep Codex users happy with usage limits and other issues.
Tibo is still sharing updates but I wonder what’s happening behind the scenes.
Are they focused on fixing Codex or are they working on a new model that could compete with Opus?
I love Codex and rely on it for professional and personal work. I need dependable organization, phone sync, and scheduled tasks that keep running. Here’s what keeps breaking—and what I’m asking @OpenAI @OpenAIDevs to fix.




















