SushiRoll

@XMoney kind of useless without being able to put my wife on the account

Your money, on the world’s most powerful network 𝕏 Money is rolling out to U.S. Premium and Premium+ subscribers starting today

Trump folded himself into a pretzel for Israel, ruined his reputation for Israel, messed up America for Israel and they still hate him for saying he’s saving Israel because it suggests they couldn’t do it without him. They expect 100% subservience & have zero loyalty in return.

@rirokpik @FreedmenUSA I think it’s you that missed it.

@FreedmenUSA Did you really get the point?

"Get over racism." Four Black Haitian women were found beheaded after being deported by ICE. Why aren't we hearing about it? Because they aren't white.

@rirokpik @MikemanCommeth Did he stutter?

@MikemanCommeth Shithole?

My workflows fork's new UI allows any agent to ask questions if they need clarity, which I feel like covers most of the times I would have used plan mode. You can see how it works (visually) with fake tickets here: t3code-board-experiments.netlify.app/#/claude-spine… vim style controls to nav between tickets, 1-9 to answer questions, s to steer.

Would you guys be upset if I outright removed "plan mode" from T3 Code?

Fun fact: this is because teachers are biased against boys. Studies have shown that when teachers don't know the gender of the students they're grading, they grade boys higher.

@RhysSullivan 💯 so fucking annoying

hi cursor friends, running `cursor {filename}` now opens the agent view by default making it not actually possible to view the file, so then you have to click on the IDE toggle, then rerun the command has added enough friction to my workflow that i might just go back to vscode

The sad thing for America First people to realize: The Republican Party is probably more NeoCon than it has been in 10 years. They probably can't win without you. But the idea that you're going to somehow wrestle internal political power away from them is a pipe dream.

literally me

I did the same, but asked for a tactical RPG (such as FFT/Triangle Strategy), it's still going, but this is the current state:

guys help me convince theo this is WAY better for a coding agent

Different locations with different natural phenomena encourage different building materials. Florida, where I live, almost all new construction is concrete brick, at least for the first floor, as we get few earthquakes but we do get hurricanes. In California, you need structures to be flexible rather than rigid to survive earthquakes.

@ferdaterd @hi_im_envy i feel like its daylight robbery for you guys. you pay roughly the same amount for wood, add a little and you get a solid brick house

spray foam insulation is a good example of like the non-american superiority complex because its like objectively better than other forms of insulation but because countries that arent america refuse to adopt it ppl just view it as tacky and bad regardless

Asimov’s Foundation series was a major influence on me. That and the fall of Rome, from which Foundation takes inspiration, is what convinced me that we need to extend consciousness beyond Earth to avoid a potentially infinite dark age.

The Matrix took its name from a 1984 novel written on a manual typewriter by a man who didn't own a computer. 42 years later, that novel finally gets its own screen. William Gibson typed Neuromancer on a 1927 Hermes portable. He coined "cyberspace" before he'd ever logged onto anything. The book swept the Hugo, the Nebula, and the Philip K. Dick award in the same year, the only novel ever to take all three. Then Hollywood spent four decades strip-mining it while calling it unfilmable. The Wachowskis lifted the matrix, the jacked-in hackers, the AI pulling strings behind a corporate veil. Every razor-girl assassin in sci-fi traces back to Molly. Johnny Mnemonic, an actual Gibson adaptation, flopped so hard in 1995 that studios treated his work as radioactive for a generation. At least five directors attached and detached over the years. Chris Cunningham in 2000. Vincenzo Natali in 2010. Tim Miller at Fox in 2017. Each attempt died the same death. By the time the technology existed to film Neuromancer, audiences had watched its ideas in a dozen movies that borrowed them first. The original became unfilmable because it looked like a copy of its own copies. Now the timing loops back on itself. A story about a rogue AI maneuvering to escape its corporate constraints, written before the web existed, lands in January 2027 as the least speculative thing on television. And one detail makes the whole arc perfect. When Neuromancer royalties came in, Gibson bought his first computer, an Apple IIc. Four decades later, Apple is the company putting his book on screen.

@theo @11MMORPG To be fair, looks like English is not his first language. Maybe X translated it wrong to his native tongue?

@11MMORPG How did you possibly misread my post this badly lol

Wait, I don't know this before. if we use fast mode we get 1M ?

@NoahKingJr When we stay at a hotel for longer than a weekend I bring and install a bidet temporarily. 😂

😭

Codex might be seriously broken right now. Yup, Codex rant part 3 GPT-5.6 Sol is burning through quota at a completely stupid rate and everyone notices it. Here’s my usage graph: Jun 23, GPT-5.5 xhigh: 327.8M tokens Jul 2, GPT-5.5 xhigh: 549.9M Jul 20, GPT-5.6 Sol High: 3.3B I had a bunch of resets, sure, and several tasks were running. That let me burn more. It doesn’t explain how 5.6 chewed through 3.3B tokens in one day. I genuinely don’t know what the fuck I would’ve had to do to get 5.5 anywhere near that. And apparently it’s not just me. @theo already covered 3 different ways GPT-5.6 was nuking usage. Looks like there might be a fourth. 5.6 uses the new Code Mode tool path. It can batch independent tool calls with Promise.all, but it barely ever does. Instead, it keeps running them one by one. That means another model cycle for every call, dragging the giant context along with it every single time. One trace found Promise.all in only 5 of 739 GPT-5.6 exec cells: github.com/openai/codex/i… My own retained logs show the same shape. After removing fork-history replay, the 5.6 peak had 23,791 model requests. My clean 5.5 baseline had 3,803. That’s 6.26x more requests, while tokens per request were actually slightly lower. It wasn’t writing much bigger responses. It was just going back to the model over and over and over again. Then someone tested explicit batching across two unrelated codebases. In the repeated High/XHigh runs, it cut model cycles by ~52–55% and weighted usage by 27–45%: github.com/openai/codex/i… I’m not saying this one thing explains every token I burned. Several tasks were active, my local rollout logs aren’t the billing ledger, and we still don’t know how much of the spike came from agents themselves. But both issues are still open, and this looks pretty fucking real. For now, I’m testing explicit batching guidance. I’m also avoiding the built-in subagent/fork workflow for long-running work and moving bounded jobs into fresh disposable Codex tasks instead. Self-contained prompt, fire and forget, inspect the result in the main task, archive it. Less context coupling, and each job is actually measurable. I hope other people can validate it, too. @thsottiaux @reach_vb @OpenAIDevs if it's true, it should be addressed. Cuz it might be THE cause.

The same female judge that gave Shiloh Hendrix a 1k fine and 200 hours of community service for saying the n word, gave a literal pedophile only 100 hours of community service, you can’t make this stuff up.

@kentcdodds Not as good as fable, but feels like the second best model on the market now. Grok is the cheaper slightly worse alternative. Not really sure where 5.6 fits in, their plans feel way too restrictive and the model produces worse code than Grok 4.5 (I prefer using it for reviews).

Have you tested Opus 5 yet? Do you feel like it's just as good as Fable (at half the cost)?