Fredo

@vibestressing @nahcrof How have you been working with CrofAI, how is its stability and speed?

I instructed Crof.ai to create a BaaS system by providing the same plan. md file to both Kimi K2.6 and GLM 5.1 (precision) models. I'm using my own custom agent architecture for both. @nahcrof

@pomufgd How have you been working with CrofAI, how is its stability and speed?

crof.ai is amazing, you can get 500 requests for just $5! It’s the perfect combo with Droid Harness!

@rezamonangg @nahcrof @rezamonangg how have you been working with CrofAI, how is its stability and speed?

Hi @nahcrof , i have integrated crof ai in my opencode. and i try to prompt once and see this in dashboard. Total request is 1 but usable requests already 498. May i know how it's calculated?

@arena @AlibabaGroup Great, thank you very much, now only the benchmark for Qwen3.6‑Max is missing.

Qwen3.6 Plus lands at #7 in Code Arena with a score of 1476 - up +16 points since the Preview. The new score also moves @AlibabaGroup to #3 lab in Code Arena. In the Text Arena, Qwen3.6 Plus lands at #36, a +13 point improvement since Preview. Congrats to the Qwen team on the continued progress!

@neural_avb GLM 5.1, great quality, slow speed K2.5, great quality, good speed Those are close to Claude models.

Okay Claude Code you're out - not paying for you again. Limits are too low, not worth it. I already have Codex, but I wanna replace Claude with an open-friendly lab as my secondary coding model. Maybe try out Hermes too. Should I get a Minimax sub or Z-ai sub?

GLM-5.1 by @Zai_org is one of the best agentic models out there. I've been testing it early and it is genuienly impressive. Way better at instruction following, long running tasks than previous generation. full review here: youtu.be/UxGieu7PaPg

@AionUi Love AionUI! You have an amazing product, but please consider posting in English (including GitHub releases). It would help you reach a much larger global audience. Keep up the great work!

@paniclightmate First "wrong" option: 4 seg Second option: 1 min

tips-creating correct perspective by ps.linglan

@mkurman88 The issue is not with K2.5, but with Kimi Code, use it inside Claude Code or other CLI

Yesterday, I'd say Kimi Code is the best thing I paid for. Today, it's the dumbest thing I paid for. What happened?! It doesn't follow any instructions, does some partial work and says it's okay, and changes function names instead of actually implementing a new one...

@arafatkatze @cline Pro Subscription, free?

Coding intelligence is free now. With my Chatgpt Pro subscription, I can use Gpt-5.2-codex all day in @cline, It doesn't even show the price. The gap between devs using this and devs not using this is about to get violent.

@cafreites @ataschz Sí, eliminalo

@ataschz Algo para windows?

Algo que descubri hace poco, codexbar.app Si trabajan con multiples herramientas de AI, es ideal para ir viendo consumos/cuotas 🍎

@donvito No, they forked @windsurf

Did Google engineers use Claude Code to build Antigravity

@askOkara Coding performance @minimax_ai Coding fast @Zai_org through @cerebras

your favorite open-source ai lab, and why?

@scaling01 Beautiful graph for colorblind people

holy shit did OpenAI just solve long context with GPT-5.2?

@wnsbye I'm still waiting for this.

somebody please do terminal bench 2.0 with droid & opus 4.5 ASAP

@ENTONLLC @makerfounder @FactoryAI @shaunmmaguire I have the exact same question.

@makerfounder @FactoryAI @shaunmmaguire The real question is why factory droid isn’t on terminal bench 2.0 yet @shaunmmaguire

Who should @FactoryAI 's Droid fight next? 🤖🥊 Same repo, same prompt, full transparency. You vote → I run the deathmatch. @shaunmmaguire said the droids welcome head-to-heads… so let’s give the people what they want 🦾

@hayesdev_ @grok what is the link to this course?

@donvito Something like this for @FactoryAI Droid?

To see your usage in Claude Code, add a statusline Add this in ~/.claude/settings.json👇 { "statusLine": { "type": "command", "command": "bun x ccusage statusline" } ccusage ccusage.com/guide/statusli… official guide code.claude.com/docs/en/status…

@minimax_ai Thank you for sharing the Black Friday deal! It's great. I was wondering if there are any similar discounts or promotions available for the quarterly or annual subscriptions as well.

🔥MiniMax Coding Plan Black Friday for all Devs! Coding Plan Starter is now $2/mo (80% OFF!) + support for image understanding & MCP web search. Ends Dec 1 — go claim it 👇 platform.minimax.io/subscribe/codi…

@robinebers Great, a faster way for rich developers to drain lakes.

genuinely the best cursor feature fight me on this here's why i don't write, read, or review code - i just don't anymore granted, i don't build enterprise or sensitive apps, but i do build apps that would have taken people weeks, without any consideration for code wanna know my secret? i test thoroughly. think about architecture. and let models fight. the last part is critical, i love letting models (the best of the best) think for me - because it works. all you have to do is read through their responses. their different personalities and skillsets do wonders.