iiinova — where your digital self keeps evolving

Arindam Majumder @arindam-1729.bsky.social · 29/09/2026

Claude Code just got REAL eval tooling. build-eval + hillclimb Auto-build evals from production traces. Then push accuracy up while cutting cost. If you're shipping agents without evals… You're flying blind 👇

100

Arindam Majumder @arindam-1729.bsky.social · 28/09/2026

Jev is the FASTEST AI model ever built for AI Agents It decides what happens next in milliseconds, at almost zero cost Most builders will use it in the wrong places In this article, I show you 10 usecases you can build with it: x.com/Arindam_172...

000

Arindam Majumder @arindam-1729.bsky.social · 28/09/2026

My latest video on 10 Jev use cases is doing really well 👀 Really happy to see the response so far. If you haven't watched it yet, go check it out. I break down some of the coolest use cases and things you can actually build with Jev. Watch it here 👇

100

Arindam Majumder @arindam-1729.bsky.social · 27/09/2026

I wrote about 10 projects you can build with @typesafeai Jev. I go over each idea, how Jev fits into the architecture, and why it makes sense for these kinds of decision-heavy applications. A fun one to build and hopefully a good evening read :) x.com/Arindam_172...

000

Arindam Majumder @arindam-1729.bsky.social · 22/09/2026

Is @grok 4.7 actually good at coding? I put it through 4 real-world tests in @cursor_ai , including a browser-based spreadsheet, calculator, Snake, and Tic-Tac-Toe. I also tested its cost, speed, and token usage. Full video 👇 www.youtube.com/watch?v=AQz...

youtube.com

Is Grok 4.7 Actually Good at Coding? I Tested Everything

Is Grok 4.7 actually good at coding?I tested xAI's new Grok 4.7 m...

000

Arindam Majumder @arindam-1729.bsky.social · 16/09/2026

The Grok Bot livestream is going crazy for a reason. An AI teammate with its own computer is a different product from a chatbot. If you want the 15-min version instead of 3 days of watching:www.youtube.com/watch?v=AHO...

youtube.com

Master 95% of Grok Bot in 15 Minutes

Learn how to use Grok Bot in this beginner-friendly Grok Bot tutori...

000

Arindam Majumder @arindam-1729.bsky.social · 07/09/2026

Scheduled 3 YouTube videos for this week. Time to be more consistent.

000

Arindam Majumder @arindam-1729.bsky.social · 03/09/2026

Working on my Voice Agents playlist. So far I've covered: → @livekit and @pipecat_ai for agent frameworks → @GeminiApp Live LLMs → @cartesia and @SarvamAI for STT/TTS models → @nebiustf for reasoning models What topics, tools, and frameworks should I cover next?

100

Arindam Majumder @arindam-1729.bsky.social · 02/09/2026

Another article made HackerNoon Top Story 🔥

100

Arindam Majumder @arindam-1729.bsky.social · 24/08/2026

Studio1 is hiring. We're looking for people who want to build AI-driven dev tools and work on real product problems. Open roles: → Social Media & Content Intern → Content Intern → Founder's Office Associate → DevRel Engineer Check the details: studio1hq.com/careers

211

Arindam Majumder @arindam-1729.bsky.social · 17/08/2026

My Latest Video on @metaai Muse Code got Ranked on Google! If you're exploring terminal-native coding agents, this one's worth watching. Watch here: www.youtube.com/watch?v=57t...

000

Arindam Majumder @arindam-1729.bsky.social · 14/08/2026

Meta is building its own coding agent. I spent some time testing Muse Code, Meta's new terminal-native coding agent. The /plan, /grill, and /goal workflow is pretty interesting, especially for longer coding tasks. Made a quick video on what I found 👇

120

Arindam Majumder @arindam-1729.bsky.social · 04/08/2026

This is what keeps me going. Seeing people actually find value in what I create is the best motivation. Thanks for the support. More coming soon. x.com/Arindam_172...

000

Arindam Majumder @arindam-1729.bsky.social · 03/08/2026

150K+ Views on YouTube! Thanks, everyone, for supporting I'll try to be more consistent with it.

000

Arindam Majumder @arindam-1729.bsky.social · 22/07/2026

Auditing invoices is painfully manual. Open PDFs. Copy fields. Recalculate totals. Hunt for mismatches. Built an Invoice Auditor with LiteParse by @llama_index + @nebiustf that does this automatically: → Extracts all the data → Checks the math → Flags anomalies 100% Open Source!

100

Arindam Majumder @arindam-1729.bsky.social · 15/07/2026

Posted random stuff on LinkedIn, and it went like this! - 113k+ impressions within 24 hrs - 500+ followers increased - Got reached out for a gig I think I should spend more time on LinkedIn

000

Arindam Majumder @arindam-1729.bsky.social · 14/07/2026

Claude Code just got a lot more powerful. AITMPL is an open-source collection of Claude Code components. Skills, agents, commands, hooks, MCPs, plugins, loops, settings, and more. All organized by category. If you use Claude Code, this repo just became essential.

000

Arindam Majumder @arindam-1729.bsky.social · 08/07/2026

cc-lens now tells you where you're burning money on Claude Code. - Low cache hits. - Premium models on tiny sessions. - Compaction thrash. - Each with a conservative monthly $ estimate. Set a budget, get a pacing projection, see spend spikes before the bill.

100

Arindam Majumder @arindam-1729.bsky.social · 02/07/2026

Just dropped a new video 🎥 Static UIs aren't going away, but AI-native apps need interfaces that can adapt in real time. In this video, I break down Generative UI, AGUI with @CopilotKit , and why the front-end is becoming the runtime for AI. Watch here:

100

Arindam Majumder @arindam-1729.bsky.social · 27/06/2026

You can replay any Claude Code session turn by turn in cc-lens. - Tokens per turn, - tool calls, - compaction events, all there.

100

Arindam Majumder @arindam-1729.bsky.social · 18/06/2026

NVIDIA dropped a 0.6B parameter speech recognition model. Nemotron-3.5-ASR. Runs on CPU. No GPU needed. • 40+ languages • Real-time streaming • 2.5x faster than official Nemo runtime • Same accuracy Works offline. Plugs into agent pipelines. Local speech processing just got lighter and faster.

030

Arindam Majumder @arindam-1729.bsky.social · 10/06/2026

Just checked my @claudeai Code Usage in CC-lens 1 billion tokens used. Didn't even realize I hit that. Been using it daily for months now. Still the most fun I've had coding in years.

000

Arindam Majumder @arindam-1729.bsky.social · 04/06/2026

Just tried @NVIDIAAI Nemotron-3-Ultra on @nebiustf playground. Gave it a reasoning prompt. Here's what it did: • 807ms time to first token • 6.5s total time • 126.3 tokens/s For a 550B MoE model, this is fast. Worth testing if you're building agents. Demo: x.com/NVIDIAAI/st...

100

Arindam Majumder @arindam-1729.bsky.social · 03/06/2026

One thing I really like about @NousResearch Agent Desktop: You can see all the artifacts directly in the interface. No switching tabs. No downloading files. Everything's just there. Tried it on Raah.dev - worked exactly as expected. x.com/Arindam_172...

020

Arindam Majumder @arindam-1729.bsky.social · 02/06/2026

Hot take: Most developers don't have a performance problem. They have a visibility problem. They don't know WHICH users are slow, on WHICH connection, hitting WHICH endpoints. That's the actual gap. And it costs you churn you can't explain.

000

Arindam Majumder @arindam-1729.bsky.social · 01/06/2026

CC-lens Crossed 500 Stars! Thanks, everyone, for supporting this project from Day 1

000

Arindam Majumder @arindam-1729.bsky.social · 31/05/2026

Last few months taught me something unexpected. How people react as you grow. Didn't see it coming from certain people, honestly. But I'm glad it happened at a small scale. Helped me understand how things actually work.

000

Arindam Majumder @arindam-1729.bsky.social · 26/05/2026

Meetings generate a lot of “we should do this” moments 😭 So we built Brieflane that turns meeting transcripts into: - Linear issues - risks - decisions - Slack updates Built with @nextjs + @Corsair + OpenAI Agents. 100% Open Source: github.com/Studio1HQ/b... Demo below 👇

010

Arindam Majumder @arindam-1729.bsky.social · 25/05/2026

The @aiDotEngineer Singapore was incredible 🇸🇬 First time in Singapore, and it exceeded expectations. Here's my recap:

100

Arindam Majumder @arindam-1729.bsky.social · 21/05/2026

Launching something in the observability space in a couple weeks. Looking for early beta testers. If you're interested in trying it out early, drop a comment or DM. Happy to share access.

000

Arindam Majumder @arindam-1729.bsky.social · 20/05/2026

Just Shipped cc-lens v0.3.3! Key improvements: • Instant boot (~0ms) via prebuilt Next.js standalone • 7x smaller footprint • Fixed Opus 4.x pricing display ($5/$25, not $15/$75) If you're seeing lower numbers in your dashboard, that's the corrected pricing. github.com/Arindam200/...

github.com

GitHub - Arindam200/cc-lens: A real-time monitoring dashboard for Claude Code

A real-time monitoring dashboard for Claude Code. Contribute to Arindam200/cc-lens development by creating an account on GitHub.

000

Arindam Majumder @arindam-1729.bsky.social · 19/05/2026

I’m starting to feel like AI agents are exposing a flaw that already existed in engineering teams: We review changes in isolation, but systems fail through interactions. Agents just scale that mismatch faster.

000

Arindam Majumder @arindam-1729.bsky.social · 14/05/2026

I'll be attending AI Engineer Singapore! If you're there too, let's catch up!

000

Arindam Majumder @arindam-1729.bsky.social · 12/05/2026

One thing I’ve noticed while working with coding agents: The issue usually isn’t “bad code.” It’s: > retries affecting another service > timeouts shifting load patterns > one “safe” local optimization causing global instability

210

Arindam Majumder @arindam-1729.bsky.social · 11/05/2026

Just asked Codex to add some features. After 10 mins:

000

Arindam Majumder @arindam-1729.bsky.social · 06/05/2026

We've been Building a new feature. Spent days overthinking it. - Workflows, - agents, - orchestration. Then we realized, just use tool calls! No agents needed. No extra layers. Just function calls. Works perfectly.

000

Arindam Majumder @arindam-1729.bsky.social · 06/05/2026

My @cursor_ai Agents SDK video is already ranking on Google. Working on a deeper breakdown now. Stay tuned.

000

Arindam Majumder @arindam-1729.bsky.social · 05/05/2026

Awesome AI Apps is Trending on GitHub! Thanks Everyone!

000

Arindam Majumder @arindam-1729.bsky.social · 05/05/2026

Shipping AI isn’t just writing prompts. You’re dealing with retries, latency, evals, cost, observability, and unpredictable failures. It’s still software engineering. Just less deterministic.

100

Arindam Majumder @arindam-1729.bsky.social · 01/05/2026

X is wild. One week everyone's hyping Claude Code. Next week they're all on Codex. I test them myself and stick with what actually works for my workflow. You should too. Don't follow the hype cycle.

000

Arindam Majumder @arindam-1729.bsky.social · 01/05/2026

Built a real-time voice agent that listens and responds instantly. - @SarvamAI STT for speech input - GPT-OSS via @nebiustf for processing - Sarvam TTS for voice output Wired everything together with @pipecat_ai into one streaming pipeline. Runs locally. No complex setup. Full tutorial:

100

Arindam Majumder @arindam-1729.bsky.social · 01/05/2026

MCP is useful. It makes integrations cleaner. But it doesn’t fix bad system design. You still need proper permissions, safe write paths, logging, and control over what the agent can do. It’s plumbing, not a safety layer.

000

Arindam Majumder @arindam-1729.bsky.social · 29/04/2026

YC is becoming the next JEE here!

000

Arindam Majumder @arindam-1729.bsky.social · 29/04/2026

The hard problem isn't storage. It's filtering. Engram by @weaviate_io solves it at ingestion: • Topics define what gets extracted • Scopes define where it lives Memory is structured before it hits the vector DB. No dumping raw logs and hoping retrieval fixes it later.

000

Arindam Majumder @arindam-1729.bsky.social · 28/04/2026

Quoting this because more people need to see how simple this gets. From blank UI → real-time collaborative editor with comments, presence, and live sync… without touching WebSockets or CRDTs. Here’s the demo 👇 x.com/Arindam_172...

000

Arindam Majumder @arindam-1729.bsky.social · 28/04/2026

Agents don’t become reliable because the model has improved. They become reliable when the system around them improves.

000

Arindam Majumder @arindam-1729.bsky.social · 27/04/2026

100% agree. We need very niche & specific benchmarks for each task/domain. That will help us to judge what works best for this use case. But my only concern is the fact that many teams will game the benchmarks. x.com/OfficialLog...

000

Arindam Majumder @arindam-1729.bsky.social · 26/04/2026

Had a great time speaking at @gdgkolkata's Build with AI event yesterday. Built a voice agent with web access using @livekit, @GeminiApp & @olostep. The energy in the room was amazing. People were genuinely excited about the possibilities. Here's the demo I showed:

000

Arindam Majumder @arindam-1729.bsky.social · 24/04/2026

I'll be speaking at Build with AI Kolkata by @gdgkolkata tomorrow. Will walk through building real-time voice agents with Gemini 3.1 Flash + Livekit that process audio directly for natural flow 📅 Apr 25 | 9:30 AM IST 📍 SNU, A Block Seminar Hall See you there!

000

Arindam Majumder @arindam-1729.bsky.social · 22/04/2026

New update for CC-lens 👀 Just shipped: • cmd + K navigation • cleaner session view • faster access to chats & tool calls UI feels way better now. Still 100% free & open source. try: npx cc-lens

000