Yacine

@_KanyeDev @grok is this true ? Or what is the name of this sdk ??

Flutter shipped an SDK that lets AI generate your UI in real time based on what the user actually wants. No predefined screens. No static flows. The app just... adapts. This isn't a concept anymore. It's in prod. And most devs are waiting for V1 to try it out.

@cursor_ai wondering if its kimi k2.6 with rl this time?

@karthikponna19 Goon

TELL ME ONE THING YOU CAN DO THAT AI CANNOT

@CommandCodeAI any explaination ?

OpenCode x Qwen 3.6 Plus - free, again Last time y’all treated our capacity like an all-you-can-eat buffet. We found more GPUs. Round 2.

@49agents @MrAhmadAwais DeepSeek v4 pro, i used to use minimax, opus and never reach that, the thing is there's different between the used context tokens in the session and the tokens used in the dashboard of my account

@kuskure_ @MrAhmadAwais 20k tokens for hello is rough but 2M for planning with coding is expected for an agentic workflow. depends on the model and context window size. what model are you running

Command Code is scaling super fast. As Anthropic raises prices, developers are switching to open-source models, and they're not looking back. We're adding thousands of new devs every day, the community is growing, and the Discord feed is pretty lit. Big ships coming next week!!

@RoundtableSpace I heard it is a trojan ? Anyone tried can confirm ?

A FULLY FREE CODING AGENT JUST DROPPED - DEEPSEEK V4 PRO, KIMI K2.6, MINIMAX M2.7, ALL FREE, ONE INSTALL. THE PAID CODING AGENT ERA HAS A PROBLEM.

@MrAhmadAwais @CommandCodeAI @vercel I am working on my final year thesis which is building a graph rag that reduce llms hallucinations and need to do pure api calls to test on different models that's why

@kuskure_ @CommandCodeAI @vercel honestly all the good harness engineering is in the @CommandCodeAI coding agent. and it works headlessly as a cli as well. i'd want you to use it instead of the api. but we've heard this enough and we're launching the api this week, could you share what use cases you have?

Command Code is now the 4th most used coding agent beating Kilo, OpenCode, Roo Code, and Hermes agent on Vercel AI Gateway!! three reasons i could think why: 1. First of all, yes we're going open source soon 2. Our $1 Go plan with open models is the best AI coding deal on the market. Period. 3. While other agents only cater to top commercial models, Command Code is probably the best harness purpose built for open models. More in my eng deep dives¹ on repair harness engineering below.

@mweinbach Is this max plan or pay as you go ?

You can not out-token me

OpenCode x DeepSeek V4 Flash - free for a limited time DeepSeek V4 Flash is currently our most popular model in Go Give it a try if you haven’t already

@bridgemindai Fr this is a garbage 😭

is anyone seriously using this garbage?

@Nano_696Cr Ça arrive toujours le dernier jour de la saison

Why tf this game give me all my worst mu in a row ??

@ai_for_success What they are somking over there ? Who's gonna pay for this ?

I was going through GitHub Copilot pricing changes… this is wild. They quietly changed model multipliers and some of these jumps are insane. Opus 4.6 is 9x Opus 4.5 is 5x Opus 4.7 is 3.6x Sonnet 4.6 is 9x Sonnet 4.5 is 6x Gemini 3 Pro is 6x Gemini 3.1 Pro is 6x GPT 5.1 is 3x GPT 5.2 is 3x GPT 5.3 Codex is 6x GPT 5.4 is 6x

@KuromeXhogexe Told ya last season i believe you can push even to 2.4K and here you are, you cameback stronger 🔥

23🔨

@pcshipp Opus 4.7 no diff

Which LLM is best for frontend development right now? - GPT 5.5 - Opus 4.7 - Gemini 3.1 pro

@catgirllilac We need hero that when activate it throws the bomb on tower

we ALL want a 5% hp giant skeleton buff next month

@rohannrk @llmdevguy I purchased the starter plan for 10$ just for testing, and from yesterday i worked like for 8 hours and just hit 5% of the weekly limits, and the model overall is equivalent to sonnet, so for the limits it's sooo good

@llmdevguy Is the minimax 2.7 software good? I’m considering the Starter or Plus plan, Is it a good idea to take it for a year? I am switching from Cursor

OK that was fast.. GLM 5.1 was the best model in terms of quality and price. For just few days.🙈 For this price it's still good option, but instead of 72$ I would rather pay 100$ for codex. More reliable models. For GLM go for OpenCode GO for 5 usd. 4400 requests per month is not bad to play with it. It's slow, but works. If you like it go with lite. King of value stays with MiniMax 2.7.

@Iso_exe77 @emilia_royale @emilia_royale

I have the address and iPhone model of when my account was made aswell as old receipts when i first bought things, can you everyone tag @emilia_royale for help