Ben Armstrong retweeted
Introducing 𝚒𝚜𝙴𝚟𝚎𝚗 / 𝚒𝚜𝙾𝚍𝚍, but with @typesafeai Jev + @aisdk
Now available on NPM: 𝚗𝚙𝚖 𝚒 𝚓𝚎𝚟-𝚎𝚟𝚎𝚗-𝚘𝚍𝚍
Can't wait to file tickets for IT to fix my vibeOS.
Today, we're sharing new research on Solaris, our first Interface World Model.
Solaris is a new kind of operating system that generates interactive interfaces frame by frame, in real time, with no code. We find that Solaris outperforms frontier LLMs when generating new interfaces, across structural similarity and information retention. Read more and request early access at the link below.
Was struggling to use the ChatGPT and it being so slow, Codex app is weirdly just more performant for just chat.
Will marry anyone to give a greencard, if they are willing to pay my Fable API usage.
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
I can finally justify my H2D purchase.
We probably undersell OrcaSlicer features too much.
Did you know OrcaSlicer supports printing with different nozzle sizes?
This feature was first introduced by @fever_soft in v2.2.0-beta back in 2024 (!!). In v2.4.0-alpha, IanAlexis fixed a regression, and now it works even better.
More enhancements are coming soon!
Pro tip: use percentages for line widths.
Video below 👇
A chef can't keep out of the kitchen.
I'm very confused by the statements of AI costing more than humans... Maybe on a monthly time frame? But it isn't the same amount of comparable output.
If you really think that, should put some more time in and try more tools.
TempleOS has been vibe-coding for 23 years, this is all the proof I need to not need Claude Code or Codex.
Someone needs to get Dario a drink. Sam's cooking lately.
Replying to @makeamarkery
i have not been drinking YET but ollie got me a super nice bottle of wine to celebrate 5.5 so maybe there will be some tweets tonight...
I need @t3dotcodes to finish. The remote environments are rough on Codex. Please save us @theo Lol.
Anyone else having issues with Codex Desktop not allowing you to reference files or folders on latest release?
Token efficiency is pretty awesome for GPT 5.5. On the Pro plan, you gotta run it 24/7 to be able to potentially burn through your total usage.
Feels like a solid 40% improvement of effective usage limits.
Keep cookin' @sama
GPT Pro models is hitting different. Also... much faster. Asked it to generate a drone CAD model.
Time to start vibe-modeling stuff? Lol.














