Varunkumar Nagarajan

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

@K2_181 We use it with Bedrock Opus models. Often run into latency issues.

Does anyone use claude code with AWS bedrock opus models or openrouter models? Do u run into any issues?

Today @GoogleMaps is getting its biggest upgrade in over a decade. By combining our Gemini models with a deep understanding of the world, Maps now unlocks entirely new possibilities for how you navigate and explore. Here’s what you need to know 🧵

This is the most important signal in AI right now, and most people are reading it wrong. The story isn't "AI broke Amazon." The story is that the largest cloud infrastructure company on Earth, spending $200 billion on AI this year, still hasn't solved the governance layer between AI-generated code and production systems. The timeline tells you everything: → Amazon mandated 80% weekly AI coding tool adoption → Their own Kiro agent was given operator-level permissions with no peer review → It autonomously deleted and rebuilt a live AWS environment. 13 hours of downtime. → A second AI tool incident followed months later → Last Thursday, the retail site went down for 6 hours. 21,000+ users locked out of checkout. → Today, a mandatory all-hands to address "a trend of incidents" they can no longer downplay Amazon's fix: junior and mid-level engineers can no longer push AI-assisted code without senior approval. They're calling it "controlled friction." That phrase alone should be on every engineering team's wall. The companies winning with AI coding tools aren't the ones moving fastest. They're the ones who built review gates, permission boundaries, and deterministic checks before handing agents the keys to production. Speed without governance isn't velocity. It's liability. Every team deploying AI in their dev workflow should be asking three questions right now: What permissions does our AI tooling actually have? Is there a mandatory human checkpoint before any destructive operation? Are we tracking AI-assisted changes separately in our deployment pipeline? Amazon learned this in production. You don't have to.

Amazon is holding a mandatory meeting about AI breaking its systems. The official framing is "part of normal business." The briefing note describes a trend of incidents with "high blast radius" caused by "Gen-AI assisted changes" for which "best practices and safeguards are not yet fully established." Translation to human language: we gave AI to engineers and things keep breaking? The response for now? Junior and mid-level engineers can no longer push AI-assisted code without a senior signing off. AWS spent 13 hours recovering after its own AI coding tool, asked to make some changes, decided instead to delete and recreate the environment (the software equivalent of fixing a leaky tap by knocking down the wall). Amazon called that an "extremely limited event" (the affected tool served customers in mainland China).

@aswinsamba Yes, atleast for the next few months.

@varunkumar plan is to stick to GHC for personal use?

Claude Code is super addictive. I am supposed to be heading to the airport now but opened new sessions to finish some stuff.

Government of India invokes the Essential Commodities Act, 1955, to regulate the availability, supply and equitable distribution of petroleum and petroleum products and natural gas

@aswinsamba Claude Code is my primary coding agent at work. And, I use GH Copilot for personal use.

@varunkumar what are you using it for?

25$ per PR for fixing your own issues, Claude? @claudeai

Now: Commuting. Clauding. Airporting. Churning. 🚕💻

India is too good in this format. Champions 🏆 #T20WC2026

MacBook Neo just dropped. $599. A18 Pro chip. Ships March 11. It's over for Mac Mini. OpenClaw has a new home.

Prof. Donald Knuth opened his new paper with "Shock! Shock!" Claude Opus 4.6 had just solved an open problem he'd been working on for weeks — a graph decomposition conjecture from The Art of Computer Programming. He named the paper "Claude's Cycles." 31 explorations. ~1 hour. Knuth read the output, wrote the formal proof, and closed with: "It seems I'll have to revise my opinions about generative AI one of these days." The man who wrote the bible of computer science just said that. In a paper named after an AI. Paper: cs.stanford.edu/~knuth/papers/…

@_vgnsh @trq212 I have used hooks and a local TTS to achieve this.

@trq212 Make claude code talk back to me!

Voice mode is rolling out now in Claude Code. It’s live for ~5% of users today, and will be ramping through the coming weeks. You'll see a note on the welcome screen once you have access. /voice to toggle it on!

Claude is down status.claude.com/incidents/0ghc…

@varunkrish Stay safe. Take care.

Finally landed back in Doha and at gate but still not allowed to deplane due to some security alert’s which popped up on all phones

Anthropic Series G is led by some large financial institutions including our parent group @DEShawGroup @arcesium

@awsdevelopers AWS

Reply to this tweet with "AWS" and we’ll tell you which AWS Service you are