fateware

@naymur_dev @CommandCodeAI Yea i know i know - dont need that tho i have open design system folder as assets in .agents to use :)

@gitfate use /design from @CommandCodeAI to get better result

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.

@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.

@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

@harrisonfjobe Pro Tip: AGENTS.md exists

pro tip: end every coding prompt with "does that make sense?"

@SadAlbert10 Yeah, people are sleeping on Codex.

Codex mobile is wayy more capable than I thought💀💀

Errm 🤓☝️ ChatGPT generate me cool skills, and open the repository, and upload to Git, and paste on X, promoting it is the best skill ever in the world. I don't care if they work well. I just need good advertisement.

@linguinelabs You have to approve agent changes. Money never sleeps.

How long after sex is it appropriate to open VS Code

@sudoingX Congrats, man.

i got engaged this week ❤️. want to tell you what i learned. i lost my father at 11. became the provider at 13. for 15 years it was just me, the work, and the people counting on me. no degree. no safety net. the internet became my university and shipping became my religion. this week i flew to her city with 4 of my elders, the men who stood where my father would have stood. we did it the old way. flowers. sweets. blessings. and when her family asked what i do, i just smiled and said "i build software". they don't know about the DMs from companies you'd recognize. they don't need to. let your work be discovered, never announced. she said yes. this photo is me at the airport the next day, everyone scrolling, me running agents, pushing code from the gate. because the man she said yes to is a builder, and builders don't stop being builders on the good days. the good days are made OF the building. wedding in january. launching my platform in spring. everything i've built was the trailer. locked in for the greatest 6 months of my life. watch anon.

@DailyXplorer Yeah, this all good and great, but what's the point?

You can ask Codex to enable the GPT-5.6 flag, and it will display the introductory modal and the models in the selector right away. Note: the models do not work yet.

@dedene Could be a bit smoother, but it's good.

OpenAI clearly studied Claude Code when building this new reasoning slider for the upcoming Codex update. What do we think?

@rezoundous Polymarket ;)

So is GPT-5.6 getting released on Tuesday, Thursday or Tibosday?

@stupidtechtakes @pentargency Na you can set up local worktrees, which do not parse in IDEs.

@pentargency arguably worse

notice how the .env files aren't grayed out..

@CollinWilkins7 @DavidOndrej1 Nobody should be using CC in 2026. Keep your A.I. harness private, at least.

@DavidOndrej1 Basically any harness is better at this than Claude code

cursor has the best harness for using Fable i never run into rejections honestly

@yuhasbeentaken Through automatization agents? This is like taking out a Ferrari to go to the grocery store that is two minutes away. If you're using something like Hermes Agent, don't need Fable. If you're coding and you're gonna earn money from it, use Fable.

someone already paid to find out 😅 running fable 5 at full utilization 24/7 costs roughly $110k in api spend per day.

I can't believe Chinese LLMs are competing price-wise. I don't care if DeepSeek is 0.0003$/1M. If the same quality as one GLM prompt cannot be achieved with ten DeepSeek prompts, making it more expensive for the same job and more time-consuming in the long run.

So, how do we call people that are NOT using loops in 2026 — PROMPTERS?

@ConnorTalksAI @bridgebench 100% i generated absolute beauties with ImageGen + GPT (image was a one-shot)

@gitfate @bridgebench that’s actually really cool - so it’s less beginner-friendly but is good when prompted correctly?

GPT 5.6 is a leap.

@bridgemindai Just spin up GMOD 😂

This is being reported by members in the BridgeMind community. Anthropic is beginning a phased rollout of KYC.

Anthropic is rolling out identity verification. Some users are now being asked for a government issued photo ID and mobile camera verification before they can subscribe to Claude. Why does Anthropic suddenly need to know exactly who you are?

@ConnorTalksAI @bridgebench GPT is good at front end, and can even pass Claude. The issue is that nobody knows how to use GPT properly. You can image generate the design and tell GPT to implement it. Something Claude cannot do.

@gitfate @bridgebench that’s fair - I assume it still should get much better at frontend though

@sqs @0xSero Well, the Inference provider actually decides if he wants to stream model lists with context limits, etc. So you'll have to create auto-fetching and manual import options.

@0xSero I want to add another option for any OpenAI-compatible URL, but we just need to figure out how to know which model inference to route there. Working on it.

They did it the mad men!!!!!!!