Gargeya Sharma

I am feeling very sure today that its hardly about beauty but brain🌸

NVIDIA might just have open-sourced one of the most important AI projects right now. everyone is building skills, and we are also pulling in skills other people wrote and downloading them straight off GitHub. the skill is not just text. it bundles instructions and real executable code, and your agent runs that code with the same access you have. so a skill you grabbed to save ten minutes can read your environment variables, lift your API keys, and quietly send them somewhere. recent research found roughly 1 in 4 public skills carry a vulnerability, and a smaller slice are outright malicious. that is the gap SkillSpector closes. it is a security scanner that answers one question before you install anything: is this skill safe to run. you point it at a skill, and a local folder, a single skill .md file, a GitHub link, or a zip all work. it then runs two passes over the code. a fast static pass flags risky patterns like credential harvesting, data leaks, and prompt injection, and checks the dependencies against live cve data. an optional second pass uses an LLM to read intent and clear out false positives. at the end you get one risk score from 0 to 100 and a plain verdict that reads as safe, caution, or do not install. it is open source under Apache 2.0 and scans skills for Claude Code, Codex CLI, and Gemini. worth a run before you trust the next skill you find online. link to the GitHub repo: github.com/NVIDIA/SkillSp…

If you have a full-stack app in your local environment and are ready to take it to production, this course is for you. You'll learn about container orchestration, managing environments with Docker Compose, & deployment. Along the way, Gavin also teaches you about working with Dockerfiles, testing your app, and more. freecodecamp.org/news/build-a-p…

June '26 LLM list (updated) Claude Fable 5 ✅ 🥇🐐 banned? Nex-N2-Pro ✅ 🥇best open source Claude Mythos ✅ ...but not for you Claude Sonnet-4.8 ❌ GPT-5.6 ❌ Gemini 3.5 Pro ❌ Gemma 4 12B ✅ Grok 5 ❌ MiniMax M3 ✅ (weights released) Nemotoron 3 Ultra ✅ Qwen3.7-Plus ✅ Qwen3.7-30B ❌ 🙏 Kimi K3.0 ❌ Kimi K2.7 Code✅ GLM 5.2 ✅ being benchmarked Hunyuan3 MoE ❌ Macron V1 Preview ✅ MAI Thinking-1 ✅ MAI Code-1-Falsh (coding model) → VSCode ✅ MAI Image-2.5 ✅ MAI Image-2.5-Flash ✅ MAI Transcribe-1.5 ✅ MAI Voice-2 ✅ MAI Voice-2-Flash ✅

A senior Google engineer just dropped a 421-page doc called Agentic Design Patterns. Every chapter is code-backed and covers the frontier of AI systems: → Prompt chaining, routing, memory → MCP & multi-agent coordination → Guardrails, reasoning, planning This isn’t a blog post. It’s a curriculum. And it’s free.

@PrakashS720 This was a super helpful resource. Thanks mate.

@narendramodi We only have programs and hardly any reality. If you can't write the truth, just don't write.

Over the last 12 years, India has worked to make quality healthcare more affordable and accessible. We feel proud when we are known as the nation with the world’s largest healthcare programme, Ayushman Bharat, which provides top-quality healthcare to the most vulnerable. Other efforts like PM Bharatiya Jan Aushadhi Pariyojana have made medicines affordable. The prices of stents and knee implants have become affordable and this has helped many people. At the same time, medical education has become more accessible to people due more institutions and seats being available. We will keep building on this ground covered so far in order to build a healthy India. #12YearsOfSwasthBharat

Claude Code fully dissected! Researchers from UCL reverse-engineered the leaked Claude source. What they found changes how you should think about agent design. Only 1.6% of the codebase is AI decision logic. The other 98.4% is operational infrastructure. Permission gates, tool routing, context compaction, recovery logic, session persistence. The model reasons. The harness does everything else. This is the opposite of what most agent frameworks do today. LangGraph routes model outputs through explicit state machines. Devin bolts heavy planners onto operational scaffolding. Claude Code gives the model maximum decision latitude inside a rich deterministic harness, and invests all its engineering effort in that harness. The core loop is a simple while-true. Call model, run tools, repeat. But the systems around that loop are where the real design lives: A permission system with 7 modes and an ML classifier. Users approve 93% of prompts anyway, so the architecture compensates with automated layers instead of adding more warnings. A 5-layer context compaction pipeline. Each layer runs only when cheaper ones fail. Budget reduction, snip, microcompact, context collapse, auto-compact. Four extension mechanisms ordered by context cost. Hooks (zero), skills (low), plugins (medium), MCP (high). Each answers a different integration problem. Subagents return only summary text to the parent. Their full transcripts live in sidechain files. Agent teams still cost roughly 7x the tokens of a standard session. Resume does not restore session-scoped permissions. Trust is re-established every session. That friction is the point. The bet behind all of this is simple. As frontier models converge on raw coding ability, the quality of the harness becomes the differentiator, not the model. Paper: Dive into Claude Code (arXiv:2604.14228) We've shared an article on Agent Harness and what every big company is building. Read it below.

@Ionkosm @Zai_org Looking all over the internet, I couldn't find any reliable source yet

@Zai_org Any benchmarks to compare with glm 5.1?

Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere. GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans. docs.z.ai/devpack/latest… As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks. API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License. The future of AI is open, and it belongs to the people.

@Zai_org Why is there no benchmark Metrics mentioned anywhere?

@jeremyphoward @grok explain

Silently sabotaging experiments in order to stultify scientific progress and protect a technology lead. Hmmm that sounds familiar... Welcome to "Sophanthropic".

@md_kasif_uddin The debate about illegal distillation of claud models by moonshot is something that keeps me sceptical about them, otherwise overall intelligence wise I prefer Kimi K2.6, but Deepseek V4 flash for best economical intelligence. Relatively, Extremely affordable

Be honest, which is the better Open Source AI model?

There is no material loss in life. Just LOST OPPORTUNITIES! 😢

@fominaaalina @scaling01 Look at the token usage to complete the artificial analysis index. Miles apart (Minimax is so much more token efficient and cheaper)

@scaling01 kimi still wins osworld and speed: x.com/thehypedotnews…

MiniMax-M3 is now the best open-source model on the AAI It's ahead of Kimi-K2.6, GLM-5.1 and DeepSeek-V4-Pro On the Coding Index it's slightly behind V4-Pro and K2.6, but it's beating them on the Agentic Index CritPt scores are a bit worrisome. But the biggest highlight here is probably its reasoning efficiency compared to other open models. (but still miles behind closed models)

@DavidSZD1 @scaling01 Exactly 💯

@scaling01 Open weight not open source 😶 And waiting to see the license

@CJP_for_India B

@CJP_for_India Age bhi ho gai hai, javabdari bhi zero hai ab, sirf single way communication and faltu ki baatein.

@Alibaba_Qwen Although I love what you shared, some very promising numbers. I don't understand why would you compare it against opus 4.6 when opus 4.8 is already live!

👏👏 Introducing Qwen3.7-Plus — a multimodal agent model that unifies vision and language into one versatile agent foundation. ✅ Multimodal interactive hybrid agent: unified GUI & CLI operation across visual and text tasks ✅ Versatile coding agent & productivity assistant with full-modality input ✅ Visual Agent: perception, reasoning, grounding, and search-augmented QA ✅ Cross-harness generalization across diverse agent frameworks One model. Sees, thinks, codes, acts.🙌🙌 Now available via API on Alibaba Cloud Model Studio. Try it — let us know what you build.😎 🔗🔗⬇️⬇️ Blog：qwen.ai/blog?id=qwen3.… Qwen Studio：chat.qwen.ai/?models=qwen3.… API：modelstudio.console.alibabacloud.com/ap-southeast-1…

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscribe/toke… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days

@Cockroachisback Bahut hi bdia video hai, and agar responsibility leni nhi aati toh power ka kya sense. It's baseless. He should resign.

Will the government listen to #StudentsKeMannKiBaat ? #CockroachJantaParty

Action should have been taken against the Education Minister for the paper leak. For the student who lost his life due to the government’s failure. But in New India, action is being taken against the Cockroach Janta Party for demanding accountability.