fateware
183 posts
fateware
@gitfate
https://t.co/nBgnfGS0q8
Nvr at the same point in space 参加日 Mayıs 2026
139 フォロー中2 フォロワー
This might be obnoxious to say but these images could just be so much cooler.
Why is the sun representing the model covered by the text, why are Terra and Luna also present, why is the composition so basic and nondramatic.
OpenAI@OpenAI
GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday. We’re expanding preview access globally now.
English
@thekitze Fable might edge out 5.6 on 3D modeling and UI/UX. Everything else, 5.6 wins or ties. Math, science, probably coding too. We'll see tomorrow.
God tier setup is probably Fable leading with 5.6 sub agents
English
samuel altman when he reads "not as smart as fable" after giving theodore early access
GIF
Theo - t3.gg@theo
Apparently I'm allowed to talk about GPT-5.6 now? It's a damn good model. Not quite as "smart" as Fable, but it is incredibly capable. Fixed all the problems I had with GPT-5.5. It is incredibly determined. Will run for a day without even using a /goal. It understands subagents incredibly well and is great at orchestrating. It's super pleasant in use cases like OpenClaw and Hermes Agent. It knows iOS dev incredibly well. It has rough edges too, but FAR fewer than 5.5 did. For many things, gpt-5.6-sol will become my obvious default. I will share a lot more soon 🫡
English
@nummanali @danshipper @every Just wait until Thursday. Don't listen to these people that have no idea what they're talking about.
English
GPT-5.6 is like a Porsche, Fable is like a warp drive.
We've been testing internally @every for about a month. And GPT-5.6 is the best combination of power, speed, and performance for your day to day knowledge work and coding.
Fable is a different beast. If you need to get across the galaxy use Fable. If you need to get around town using the best available tool for the job, use 5.6
Full vibe check dropping tomorrow!
English
yo @sama if sol still produces this level of slop i am canceling my subscriptions and moving to banthropic
English
@EA888B8 @thekitze @sama Maybe because even a dumbass would realize that GPT has image generation capability, connect 2 and 2 together. -- You run Codex. You prompt it to generate template images. You choose one. It makes it perfect, real quick, real fast. Elevates GPT's front-end capabilities tenfold.
English
thank you anthropic for extending my 0% left fable quota for a few days
Claude@claudeai
We're extending access to Claude Fable 5 on all paid plans through July 12.
English
5.6-sol got postponed to the 12th damn
Claude@claudeai
We're extending access to Claude Fable 5 on all paid plans through July 12.
English
GPT-5.6 Update
- GPT-5.6 is not launching today. The rollout has slipped again.
- It's still expected to launch this week, with Thursday currently having the highest chances.
English
@naymur_dev @CommandCodeAI Yea i know i know - dont need that tho i have open design system folder as assets in .agents to use :)
English
Comparing GLM 5.2 vs DeepSeek v4 Pro
Everyone is talking about DeepSeek v4 Pro will overpower GLM 5.2.
So I ran a test using /design features from Command Code
GLM 5.2 costs $0.032, and DeepSeek-v4-Pro costs only $0.00052.
Based on pricing and overall design, I’d say DeepSeek wins. But if you’re only focused on design, then GLM 5.2 wins
OS models only work well when you’re using it with the right harness.
English
@naymur_dev From my personal testing, that wasn't the case but ok... sure I have specific tastes - to be fair tho hooking up a design system to both glm and ds4 could produce same/simillar results.
English
@gitfate Yeah, but I didn't find that you need 10 or 20 prompts, You just need 1-2 more prompts to fix the design with DS4
English
pro tip: end every coding prompt with "does that make sense?"
English
