Not everything you save should stay. UNTIL is your iPhone's temporary memory: local, offline, with no account, cloud, ads, analytics, or tracking. Free on the App Store: apps.apple.com/app/until-tem… #UntilYouNeedIt #UNTILapp

Parking. Wi-Fi. Ticket. Receipt. Some information does its job. Then life moves on. UNTIL: temporary memory for iPhone. Free on the App Store. apps.apple.com/app/until-tem… #UntilYouNeedIt

The most urgent memory is often the one that lasts the least: where you parked. Keep it for the moment you need it. Then get back to your day. #UntilYouNeedIt

The most urgent memory is often the one that lasts the least: where you parked. Keep it for the moment you need it. Then get back to your day. #UntilYouNeedIt

Parking. Wi-Fi. Ticket. Receipt. Some information does its job. Then life moves on. UNTIL: temporary memory for iPhone. Free on the App Store. apps.apple.com/app/until-tem… #UntilYouNeedIt

Codex limits are in the gutter now. Using 10% weekly limit in an hour is crazy. My usage patterns haven’t changed but something has.

Codex limit is messed up. just got a reset today and its already down to 79 %

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/issu… 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/issu… 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.

Glad everyone else is noticing that Codex usage limits have been destroyed. >It’s draining as fast as 5hr limit. But weekly >Cheaper models, are seeming to drain our quota just as fast. >20x plans feel like 5x “5.6 is extremely efficient, and costs just as much as 5.5” yeahh right.

For years, I used AI to write, research, and think better. This time, I used it to build (and I’m not a developer…) With Codex and GPT-5.6 Sol, I developed my first iOS app: UNTIL. I’ll be launching it soon. They didn’t build it for me—they helped me learn faster, iterate faster, and turn an idea into a real product. It still feels like we’re only scratching the surface of what’s possible.

How can we leverage a large community of Italian builders? What can we get from it? I'm talking about the Italian Builders community I launched last Saturday, which has already reached almost 500 members.

That’s what we need.

Aka open source

The future of AI belongs to underhyped and overcapable public models.

There has never been a better moment to develop EU AI labs.

As expected, Google and Apple are going to get married. A wonderful future ahead for Apple and Google users.

Nice

Sora 2 flickers. we fixed it and made it unlimited. Introducing Higgsfield Enhancer. it eliminates flicker in any video. AI generations, old footage, anything. try it with Unlimited through end of week. + new Sora 2 MAX models & Higgsfield Upscale Preview. RT & reply next 9h = 200 credits in DM!