@elonmusk The universe is *really* that big. It's *very* likely we're among the first...
...or the last. But with the nature of space-time itself and the volume of the visible universe + the difficulty in finding a way to make any of it matter, tangibly; It's a lonely place for a species.
I just really want to say FUCK YOU @Cloudflare - And while we're at it, same to you sad, a-holes hiding behind a layer of a-holes who make the 'net a waste of time. Not that I'd *want* to use your shitty sites if I had a first, better, choice until you provided it for me. 🤬
I can't help but imagine how incredibly productive, fast and more accurate than AI, humans would be if people got off our balls and let us focus on one thing at a time. Interrupt your agents withj something that came through on a heartbeat while mid-task. See what 2 subjects do.
Watching Codex click away at desktop icons that haven't been configured as actual icons yet (only the system menu icons work) as it tries to test the the new app I loaded in for it to finish working on... Feels, mean. I should probably tell it... 🤣
Your ChatGPT subscription now powers an OpenClaw agent that genuinely feels magical to talk to.
Previous OpenClaw releases had OpenAI models running, but they never quite let the models reach their full potential. That changes today.
Personality is now deliberate, tool calls land exactly where they should, and your agent actually follows through on what it says it will do.
OpenClaw is now running on top of the Codex harness by default. In handing the inner loop to OpenAI's native Codex harness, we eliminated the conflicting instructions and duplicate tools that used to make the model hesitate.
What we stripped out under the hood:
- Duplicate tools (no more guessing between Codex native vs OpenClaw versions)
- Conflicting instructions (no more NO_REPLY vs message tool ambiguity)
- Leaked context (heartbeat logic only appears on actual heartbeat turns)
Less context bloat. More room for the agent to think.
And here's what we inherited for free, thanks to the Codex App Server:
- Searchable dynamic tools. Roughly 5,500 fewer upfront tokens per turn, which means faster and cheaper.
- Auto-Review mode using the built-in Codex guardian.
- OpenAI's native plugins (Calendar, Email, Drive) running in the same thread.
For you, the result is a personal agent that actually feels personal. It picks up where you left off across any channel, handles things before they hit your radar, and only breaks your flow when it has something genuinely worth showing you.
For developers, the result is stability. Because the inner loop runs on OpenAI’s native Codex harness, every upstream improvement lands in your agent automatically.
To get started, paste this in terminal:
> openclaw onboard
That is the whole setup.
@steipete@briantwotimes@sama And where it's at when things smooth over again... Might just converge on a very nice sweet spot. Right now it just feels like being an addict and thinking "I should just stop until my drug of choice is pharmaceutical grade." Then again I bet addicts don't think like that.
@The_Sourkraut They can. They should. They care too much what people think. The Futuristic 80s and the "World of Tomorrow" atomic era 50s have some of the best designs.
Death Valley National Park is experiencing its first major superbloom in a decade as of March/April 2026, driven by record winter rainfall (1.7 – 2.5+ inches) that transformed the desert landscape with vibrant carpets of yellow, pink, and purple flowers.
https://t.co/YgaHskYSlM
Well don't fucking repost itl, hahahhaha, because that's so hilariously obnoxious; anyone with any empathy (or stupid and feeling annoying, like me) is going to feel your pain and be compelled to offer sympathy! haahhahaha fml
25 AI agents started failing with what looked like DNS. It was 2 bugs behind 1 bad error: a dead resolver and Cloudflare rejecting bot-like headers. I wrote up the breakdown and both fixes:
https://t.co/P8bIFmLZBh