Aryan Pardeshi

@AIatMeta muse image model is soo good.. tried it at arena ai

@StudentOffersHQ not available for india sadly

$500+ worth of paid AI models. Free. No card. Access GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro & flash, Qwen3.7 Max and more. Qwen Cloud has the most generous AI free tier going: → 246 models: LLM, vision, voice, video → 1M tokens on each of 120+ LLMs → Free for 90 days How to claim: 1. Sign up at Qwen Cloud 2. Free tier activates automatically, no card 3. Grab your API key, start building 1M per model runs out fast, so put LiteLLM in front. One endpoint that tracks every quota and auto-switches models when one runs dry. Plugs into any coding agent — Claude Code, Codex, Cursor, Hermes, OpenClaw & more.

@0x0SojalSec react icons and elements...

Why do 97% of the vibe coded websites looks like this?

@KMbappe mbappe my goat

Encore un peu plus près… 🇫🇷💪🏽🙏🏽

@finkd I have tried it on arena ai it's veryy good

(1) Today we're releasing Muse Spark 1.1 -- a strong agentic and coding model at a very low price. It's available through our new Meta Model API and in Meta AI.

New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.

@PythonPr convenient and easy to understand

Why do programmers love if else?

@md_kasif_uddin anthropic

Be Honest, Which AI company do you trust the most?

@yuhasbeentaken @TheHBrand totally

@TheHBrand same Gemini 3.5 flash should be way higher

deepseek v4 is terrible at hallucinations... >deepseek v4 pro scores 94%. >deepseek v4 flash is even worse at 96%. for comparison: >glm-5.2: 28% >mimo v2.5 pro: 25% >minimax m3: 16% lower is better. this means deepseek often answers confidently even when it should admit it doesn’t know. use glm-5.2 for execution... but never trust the output without tests, verification or a second model reviewing the work!!!

Built a multi-agent AI research assistant during this week. LangGraph + FastAPI + SSE + Docker. Parallel agents, human-in-the-loop approval, real-time SSE streaming UI. Not a tutorial. Not a wrapper. From scratch. github.com/Aryan-Pardeshi…

@0x0SojalSec A Corolla that outruns Ferraris

Fable 5 Frontier-level coding intelligence locally on 4.5GB VRAM Gemma 4 with Coder-Fable 5 reasoning traces specialized fine-tune distilled from execution-verified CoT reasoning traces of Composer 2.5 & Fable 5 brings higher-level thinking to local setups Result? A model that It thinks step-by-step deeply about problems, then outputs clean, working code, complex algorithms, debugging etc all running privately on your laptop

@israfill @dr_cintas No more need for workarounds for scraping ig

@dr_cintas this is really helpful for x scrapping

your AI agent can now read all of X from inside Claude, Cursor or Copilot, and you don't have to build a single thing to make it work. X just turned on what's called a hosted MCP server, which is really just a ready-made bridge that lets your AI talk to X directly. Before this you had to build and run that bridge yourself, now X runs it for you. once it's connected, your agent can: → search posts and look up any user → read and organize your bookmarks → pull data and draft articles → reach 200+ X tools through one link it's read-only for now, so it can look things up but can't post for you yet. what you get for $0: → nothing to build, host or keep running → no stitching 200 different tools together yourself → it works inside the AI app you already use what it used to take: → writing and hosting your own bridge to X, basically a weekend of work → connecting the X API piece by piece → handling login tokens by hand in your code how to set it up (about 5 minutes): 1. make an X developer app once at developer.x.com, this is just the account that's allowed to talk to X 2. install xurl, a tiny helper from X that logs you in and keeps you logged in, so you never deal with tokens 3. point your AI app at api.x.com/mcp, which works with Claude Desktop, Cursor, VS Code with Copilot, and Grok Build 4. now just ask it something like "find the top posts about MCP this week" and it pulls the answer straight from X why this is a big deal: X is the first major platform to host its own MCP, so hooking your AI up to it went from a weekend project down to a five-minute setup, and pretty much every platform is going to copy this next.

@israfill kk

@Jasper_ARYAN Resets in 3 hr 33 min

giving away a FREE MiniMax API key worth BILLIONS (330M+ tokens daily, No Rate Limits) 😳 All MiniMax models included: Language Models: • MiniMax-M3 (Frontier coding, 1M context) • MiniMax-M2.7 • MiniMax-M2.7-highspeed • MiniMax-Text-01 • MiniMax-VL-01 (Vision-Language) Video Models: • MiniMax Hailuo 2.3 (Video Gen) • MiniMax Hailuo 2.3Fast (Video Gen) Voice/Audio Models: • speech-2.8-hd (TTS) • speech-2.8-turbo (TTS) Image Models: • Image-01 (Image Gen) Music Models: • Music-2.6 (Music Gen) • Music-Cover (Cover Gen) API Key: sk-cp-F2WaIZegsKCeqoeET4Nuwngt3Nc1gjJx1VExfFkhCLNMUhmHi3TE3N59ZpriTi7nQPR_k-NQXro6xOiQdxt-QvQJr_kmDopsgOU37Jp4kX_vL3PxX99MuGQ bookmark this and use it with any OpenAI-compatible client

@israfill Thanks using it for my personal project wont burn much promise💕🫡

dropping ANOTHER free MiniMax API key worth $2000+ (last one burned 2.6B tokens in 7 days, No Rate Limits) All MiniMax models included: Language Models: • MiniMax-M3 (Frontier coding, 1M context) • MiniMax-M2.7 • MiniMax-M2.7-highspeed • MiniMax-VL-01 (Vision-Language) Video Models: • MiniMax Hailuo 2.3 (Video Gen) • MiniMax Hailuo 2.3Fast (Video Gen) Voice/Audio Models: • speech-2.8-hd (TTS) • speech-2.8-turbo (TTS) Image Models: • Image-01 (Image Gen) Music Models: • Music-2.6 (Music Gen) • Music-Cover (Cover Gen) API Key: sk-cp-2op75F4rtXvmq5gj2lfOvoulnDUZNzhGcRMKQstV5IdqtH4TVp4mi0DHb3EeFfB8gnes2Ct7njUtpY4hc5lLHb0hSG2eTVoCNJmHOq2V973P_0k5hlidtU0 bookmark this and use it with any OpenAI-compatible client

lol. we're so back.

I really love the @LangChain docs so much whenever i read them they always help so much. Thanks Langchain team for putting so much effort in it.

We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality: - GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81) - Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls - GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build. Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!

i keep hearing about how GLM-5.2 not only is great at coding but also that is on Opus 4.8 level when it comes to front end design I wanted to find out so... i put it to the test.. you can be the judge

@elonmusk @teortaxesTex won’t take that long