Aadarsh (@Sable_Do) header
Aadarsh (@Sable_Do) profile picture

Azure Cloud and DevOps Engineer ☁️ Cloud, AI, Tech, Random thoughts. Sharing things I find interesting, useful or worth talking about ✌️

Indore
Joined May 2018
FOR 30 YEARS, INSTALLING A SOFTWARE UPDATE PROTECTED YOU. TODAY, GOOGLE CONFIRMED THAT RULE IS DEAD Google Threat Intelligence Group Just dropped a report officially stating: "The era of autonomous attacks have arrived" Most accounts on X are just reposting the two sentence headline, but if you actually read the technical breakdown Google and Mandiant just published, what they caught running in the wild is terrifying: 1. The "Patch to Exploit" Trap (exploit_agent) - Google uncovered an autonomous LLM framework on an exposed staging server called exploit_agent. The second a company publishes a security patch, this AI compares the code before and after the fix, reverse engineers the exact vulnerability the developer just patched, writes a working exploit, and attacks unpatched servers automatically with zero human involvement. 2. Multi Agent Hacking Swarms (ARTEX, CAIRN, PentAGI) - Threat actors aren't sitting at keyboards typing commands anymore. Google confirmed Attackers are deploying multi agent swarms where different AI models split up the intrusion, one scans the network, one writes the exploit, and one drops web shells. They already caught CAIRN targeting the US aerospace sector. 3. Poisoning Developer Coding Assistants - The report reveals espionage groups are now manipulating autonomous AI coding assistant configurations so software engineers unknowingly drop back doors into their own company codebases during local execution. Look at Google's literal conclusion in the report: "Defending against machine speed threats at human speed isn't feasible" How long until human security teams are completely locked out of the loop and cybersecurity is just defense AI's fighting attack AI's at millisecond speed?
Hackers are now using LLMs to continuously scan software updates, spot newly fixed bugs, and build attacks before teams can apply the fix — all without human involvement. That’s according to the latest report from the Google Threat Intelligence Group. We're helping defenders counter automated threats with Google AI Threat Defense, which combines Gemini and other frontier models to find and fix flaws before attackers can exploit them.
11
4
1
24
1,919
Aadarsh retweeted
i never thought i would enjoy talking to strangers on the internet this much. some people share ideas, some share their work and some just make your day better with a simple reply. thats a nice side of X.
5
1
13
271
When I started learning agentic AI, I kept running into three names: LangChain, LangGraph, LangSmith. They sound almost the same. What does each one actually do? Do you need all three? Let me clear the confusion for you in 30 seconds. >> 𝗜𝘁 𝘀𝘁𝗮𝗿𝘁𝘀 𝘄𝗶𝘁𝗵 𝗮𝗻 𝗟𝗟𝗠. It can answer questions, write code, and summarize documents. But it can't reach your database, call your APIs, or remember last week's conversation on its own. So developers wrapped code around it: prompts, document retrieval, API calls, output parsers. Everyone ended up writing the same glue code, and switching models meant touching the whole app. >> 𝗟𝗮𝗻𝗴𝗖𝗵𝗮𝗶𝗻 𝗳𝗶𝘅𝗲𝘀 𝘁𝗵𝗶𝘀. It gives you ready-made building blocks to connect models, tools, retrievers, and prompts into one working app. Then we see the problem - A simple chain works when every step follows the last one. - Real agents don't behave like that. If a tool fails, the agent must retry. It has to pick between two paths. It needs a human to approve an action. Or the app crashes halfway through a long task. Handling all that with loops, flags, and custom retry code gets ugly fast. >> 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵 𝗳𝗶𝘅𝗲𝘀 𝘁𝗵𝗶𝘀. You build workflows where steps can loop, branch, share state, and resume after a failure. Think of it as a stateful workflow engine for AI agents. Now you ship it. Real users are on it. Then someone says, "The agent gave me a wrong answer." Your logs look healthy. But what actually went wrong? - Was the retrieved context bad? - Did a tool return wrong data? - Did the model ignore your instructions? - Did your last prompt change break something? - And what did that one request cost? Normal app logs won't tell you. >> 𝗟𝗮𝗻𝗴𝗦𝗺𝗶𝘁𝗵 𝗳𝗶𝘅𝗲𝘀 𝘁𝗵𝗶𝘀. It traces each run, shows prompts and tool calls, tracks latency and token usage, and lets you test outputs against datasets before you roll out changes. Think of it as observability plus evaluation for LLM apps. 𝗧𝗼 𝘀𝘂𝗺𝗺𝗮𝗿𝗶𝘀𝗲 LangChain → connects LLMs to tools, APIs, and data LangGraph → manages state, loops, retries, human approvals LangSmith → traces, debugs, and evaluates quality You don't need all three on day one. - Start simple. Add LangGraph when your workflow needs state and branching. - Add LangSmith when you need to see what's happening in production. Don't try to learn every framework. Learn the problem each tool solves.
12
29
1
193
7,753
🚨 IS THE NOVEMBER 17 GLOBAL INTERNET BLACKOUT REAL? People on X are saying the internet will go down, banks will be wiped, and the world will be offline for months. @grok, is there any actual proof behind this or is it just a massive hoax? What is really happening on November 17?
149
64
7
372
694,885
BREAKING: Microsoft says it has emailed its top engineers about the Outlook outage, but none of them seem to be receiving the emails.
451
3,978
679
40,178
2,187,722
Aadarsh retweeted
Discover how Microsoft is using Azure Cobalt 200 VMs to accelerate electronic design automation (EDA) workloads, improving performance and efficiency for complex silicon design. Read the blog: msft.it/6012x6WEw
26
6
1
39
19,753
Aadarsh retweeted
Qwen4 is coming. Deeper knowledge. Richer world understanding. Stronger coding and agentic capabilities. Built for real-world tasks — from complex coding and knowledge work to front-end builds and professional software workflows. Qwen4-Max is now in preview on Alibaba’s Token Plan. You can also get early access to the new model on QwenWork, Qoder, Qwen APP, and QwenStudio. Put it to the test on a real problem. Show us what you build. 👀 Token Plan: qwencloud.com/pricing/token-…
987
1,541
1,074
12,731
1,406,855
Aadarsh retweeted
Big day for us at @pluraiAI ! Plurai Simulation is live and free for every AI engineer. AI agents look great in demos. Until real users break them. So we built a world where your agent can fail, learn, and get fixed before your users ever see it. → Digital twin: Your real agent, its tools, and environment recreated from your code → Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter → Auto evals: Check what your agent actually did, not just what it said → Verified fixes: Every failure comes with the run that exposed it and a fix you can verify → Replays: Turn any production failure into a simulation and replay it against every new version of your agent All inside the coding agent you already use: @claudeai code, @OpenAICodexCli , or @GitHubCopilot . Start simulating for free: simulation.plurai.ai/connect
221
343
198
1,072
1,727,526
Aadarsh retweeted
Starting to roll out today: Claude Whiteboards, Claude Sheets and Claude Data. Think a plan through on a board, build a tracker in a sheet, and tell a story with your data.
1,549
5,280
3,869
64,382
12,479,024
Aadarsh retweeted
Gemini 4 Carbon is now available. It’s our strongest model, built to dig deeper, handle long-horizon tasks, and multi-step reasoning. If Argon is great for complex tasks, Carbon is the model you bring in for your hardest problems.
675
1,111
877
10,732
2,952,941
Gemini 4 Carbon is rolling out today. It’s built for sustained, long-horizon tasks, reasoning deeply through complex software engineering, cybersecurity, and scientific discovery. Coming globally via the Gemini API in @GoogleAIStudio and Gemini for business, and for Ultra subscribers in @antigravity, the @GeminiApp, and AI Mode in Search.
571
605
265
8,569
797,266
Me looking at all the work I left pending before a long vacation.
2
7
23
2,295
Aadarsh retweeted
During pre-release testing, Claude Fable 5.2 and Claude Mythos 5.2 worked on ambitious projects in many different fields. Here are a few. From a one-paragraph prompt, Fable 5.2 designed three working electronic devices, including this home voice assistant hub.
812
2,920
1,751
43,080
7,171,311
Aadarsh retweeted
Ever noticed how Azure resources have extremely long IDs? Those paths are not random. They tell you exactly where a resource belongs and how to identify it. ☁️ Welcome to Day 10 of 20: Azure Organization and Management 📘 Azure resource identifiers Let us decode a real example.
2
1
4
53
Aadarsh retweeted
When Jensen said he loves Chinese models, I thought it was about DeepSeek and Kimi and GLM, etc……🥀
105
497
71
7,689
215,952
Cloud & DevOps to AI Engineer (90 Days Roadmap)
I’ve been mapping my own journey from Cloud/DevOps → AI Infrastructure, and this is the 90-day path I’d follow. You don’t need to start over. Build on what you already know, add AI skills, and start building production-ready systems.
1
14
65
3,526
Aadarsh retweeted
Every time you deploy a VM, Storage Account, Database or Virtual Network, you create an Azure resource. But what exactly makes something an Azure resource? ☁️ Welcome to Day 6 of 20: Azure Organization and Management 📘 Azure resources Let us break it down.
2
1
8
204
Aadarsh retweeted
Let's connect if you are into AI, cloud, software, DevOps, cybersecurity or just love learning new things.
14
1
15
407
Aadarsh retweeted
Introducing Gemini 4 Carbon, our latest frontier model. Carbon delivers improved performance across domains — ranking #1 on v5.0 of the @ArtificialAnlys Intelligence Index and sets a new state-of-the-art in cybersecurity and long-horizon capabilities. It’s rolling out starting this week to cyber defenders through our Fairwind Program, with expanded access coming soon 🧵
713
1,323
628
12,579
1,170,046
Aadarsh retweeted
GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
🤖 Made with AI
2,240
2,559
2,339
28,824
8,348,770