🧵Internetem se šíří video řidiče, který se prohnal Uhříněvsí 120 km/h, kolem školy, za bílého dne, v době, kdy tam byla spousta lidí a aut. Protože v reportáži na Prima CNN jeho identitu neodhalili, zkusím to já. Vláko 1/17
Apeluji na vládu, aby urychleně poskytla Ukrajině letouny L-159, které mohou pomoci sestřelovat novou verzi ruských dronů. Ty stroje jsme pořídili, aby nás bránily, ne aby hnily v hangárech. Je to v zájmu nás všech.
Give us a slow mode for Codex.
Something like /slow where it runs at half the speed but uses roughly half the usage. It would put less strain on OpenAI’s servers and maybe even make the 20x plan possible, right?
It’d be perfect for /goals too, just send a task before going to sleep and let it work overnight.
I’d happily trade speed for more usage @thsottiaux
Session limits on Codex/ChatGPT Plus are back, alongside another reset.
For people relying on the $20 plan to get their work done, this is a rough change.
The $20 Plus plan was one of the best ways to get access to frontier models OpenAI and still get a decent amount of work done without hitting limits.
Without the session limit, you could actually sit down and code for longer stretches instead of getting cut off and waiting for the next session.
And calling Plus users “relatively casual and new users” misses a big part of the user base. For a lot of people, Plus isn't a trial plan. It's simply the plan they can afford.
I get why they're bringing it back, but it's still a worse experience for users. Jumping from $20 to $100 or $200 just to keep working isn't realistic for everyone.
Holy Sh*t Brooooooooo... This Chrome extension is sooo perfect for LLMs. 🤯
It lets you instantly convert almost any webpage into clean Markdown, making it easier to use with ChatGPT, Claude, Gemini, and other AI tools.
Perfect for AI enthusiasts, developers, designers, & anyone who works with web content :)
Follow me for more amazing AI, Coding & Web Dev insights 💎
Sorry, @thsottiaux, but here I am again with this mess.
I've completely stopped using ChatGPT Work, Codex, and even regular ChatGPT with GPT-5.5 Instant. For the past 8 hours, I've been monitoring my usage, and my quota has dropped another 2% despite doing absolutely nothing. I've been using Gemini exclusively to avoid any ChatGPT usage during this test.
To make things even stranger, my ChatGPT profile says I've used 8.3 million Sol tokens today. From what? Which task? My last task was yesterday 1:05 PM.
At this point, this isn't about automations (they're all paused), using multiple devices (I only use ChatGPT on my MacBook and iPhone), or unauthorized tools, as some people suggested.
At this rate, I could lose 42% of my weekly quota without sending a single prompt.
Usage quotas simply cannot drain for no identifiable reason.
GPT-5.6 Sol 1M in Codex. This used to only work for API keys, but we just flipped the switch and works for usage through ChatGPT accounts now too.
The same warning applies, there is a reason the current context length is the default, we have tuned it to ~perfection. But you do you!
I've been using Google Antigravity heavily for roughly six months.
At this point I have a pretty ridiculous list of things that need fixing before Google drops another model into it.
So here's me dumping my sufferings! A thread🧵
SPD nahonila hlasy přes falešné Pauknery, ale PR agentuře nezaplatila 👌🤣🤣🤣
Založili jsme falešné účty a ovlivňovali volby, přiznala agentura u soudu. Vše odkryla, když nedostala zaplaceno | Hospodářské noviny (https://t.co/BgXtsVtbgk) https://t.co/ZiHU1WxYVz
Mně už je ho líto. Už ho někdo doražte jako starýho psa. Všichni z médií, které Půr kritizuje, jsou odpovědní za každého sponzora, ale Půr za to nemůže, protože to nesleduje 😄🤡
OpenAI appears to be working on a feature that would let you purchase a rate limit reset for Codex
Source: public checkout pricing config & ChatGPT web app assets