Bahman Pasha

What I love about GPT‑5.6 Sol in @Codex is the combination of speed and long horizon execution.

What I love about GPT‑5.6 Sol in @Codex is the combination of speed and long horizon execution. It can go deep into a complex codebase, maintain context, and actually finish the job

@sama Cant Even use it 5h Limit is to harsh

makes us happy to see people love 5.6 sol so much!

@1337_jay @thsottiaux Cant Even work with codex now, it works just for 1 h

@thsottiaux Can you do something about 5h limits? Why do we even have/need 5h limits at all? No but seriously, with 5.6 Sol Max/Ultra the 5h limits get drained too fast.

To celebrate the launch of GPT-5.6 Sol, we will reset the rate limits again (twice) across ChatGPT Work and Codex over the next 24 hours. We want you to have the time to truly try ambitious tasks and get the hang of it. Happy exploring!

@SoyRubik Receb

NECESITO un NOMBRE para este GATO 😺

@ClaudeDevs Come over here my fable 😘

We've reset 5-hour and weekly rate limits for all users.

@2the_dark_byte_ آلمانیا میگن پخمن 🥹

زنگ زدم یه جا میز رزرو کنم. طرف پرسید به چه اسمی؟ گفتم Bahman, I can spell that for you... که یارو پرید وسط حرفم گفت I know how to spell Batman.

@markksantos 🥹

fable 5 gets cut from claude subscription tomorrow claude code weekly limits get cut in half next monday cancel your subs. it's over. gpt5.6 incoming anyway

@davodm n8n هنوزم عالیه

این چیزایی که با هرمس و openclaw میسازید رو n8n هم میساخت فقط چون ترندش تموم شد سوییچ کردین؟

@uniles6 Kauf dir einen Luftreiniger, der Luft reinzieht und von oben wieder abgibt. Platziere ihn neben einem Fenster, damit frische Luft hereinkommt und du eine zusätzliche Luftreinigung hast.

Wie kann es sein das draußen 18°C sind und in meinem zimmer 30°C ich hab meine Fenster seit 4h offen

Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere. GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans. docs.z.ai/devpack/latest… As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks. API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License. The future of AI is open, and it belongs to the people.

GLM-5.2 is Fully Open, Frontier Intelligence Belongs to Everyone Today, the sudden restriction of certain frontier models is deeply regrettable. At a time when access to frontier models is abruptly cut off for non-technical reasons, we are even more convinced of one thing: science should be global. The path to AGI (Artificial General Intelligence) must never be enclosed by high walls. We have always believed that AGI should be the cornerstone for all of humanity to collaboratively explore the boundaries of intelligence and solve complex challenges, rather than a privilege monopolized by a few rules and subject to revocation at any moment. In the face of external blockades and restrictions, our attitude is one of radical openness. Frontier intelligence must remain open-source, accessible, and buildable, serving every dedicated developer. GLM-5.2 is Zhipu's most capable open-source model to date. It not only supports a truly usable 1M context window but also maintains a continuous lead in the independent completion of long-horizon tasks, providing solid foundational support for building complex agent applications. It also continues to be our main engine for creating the strongest domestic coding model. Tonight at 5:21—at this special moment—GLM-5.2 will officially be available to all GLM Coding Plan users (including Lite / Pro / Max). The API will also go live next week. A step closer to frontier intelligence for everyone. The future of AI is open, and it is for the people. ModelKey: GLM-5.2

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6. 🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates. ⚡️ 6x High-Speed Mode coming soon! 🔌 Available today via Kimi API and Kimi Code. 🔗 Kimi Code: kimi.com/code 🔗 API: platform.moonshot.ai

For the first time, I'm vibecoding with ZERO frustration and in a complete state of flow, so much so that I'm running out of ideas. Typically, I have so much backlog of things I want to add, but after Fable landed on Replit, I'm almost certain I don't need more IQ for vibecoding, just cheaper and faster models, and we're done here.

@ycombinator We give you our sessions to know if we’re night owls!? 🙄

@joawshoea I was banned two months ago, and they haven’t even responded to my inquiries.

I just got banned from ChatGPT and they gave me 0 reasoning why ??? I have to keep working with clients and I'm used to my workflow with Codex so I need information on why I got banned. Seriously confusing as I haven't done anything that I know of against TOS.

@Jchammond_ Same

Codex has been stronger for implementation quality, especially backend and business logic. Claude can get similar results, but often needs more hand-holding. Claude has been most useful for planning, reviewing, ticket shaping, and UI iteration. The biggest unlock is still being explicit about good patterns vs. anti-patterns. The better the constraints, the better the output. My current workflow: Claude for planning and shaping the work. (Opus 4.8 xhigh) Codex for building the implementation. (5.5 high/xhigh) Human review over all of it. The biggest differentiator is that I feel I can just trust Codex to get it right. With Claude I find myself being much more skeptical of the output which makes me spend more time reviewing and correcting.

@T_Zahil I also resist it until last week nice tool

Please someone explain to me why should I use Hermes if I already use Codex, Claude etc What could I do with it?

@kevinwhinnery Claude Design is currently at its peak can’t sleep anymore.

Claude Design with a company design system configured -> Claude Code/Opus 4.8 is the most busted demo engineering workflow I've ever seen (and I was already drunk on power coming from Codex/gpt-5.5)

@Scav Of course

Is anyone actually still using Obsidian?