Harsh Kumar

@raoo0o0 @BangaloreRoomi @UtkarshKaushik1 @fmrbangalore This looks awesome. Is it still available ?

We are currently looking for a 3rd male flatmate to accommodate the 3rd room, in our 3BHK in Indiranagar by the end of June. The rent would be 14.5k, the place is fully furnished. Do let us know of any leads! @BangaloreRoomi @UtkarshKaushik1 @fmrbangalore

Re: SaaS founder asking for a meeting so you can trial their software Might as well ask me to Venmo you thousands of dollars. Time is the most precious resource you have Why are meetings required to try software?

We are excited to announce that Sarvam is partnering with @PixxelSpace to power the AI backbone of India's first orbital data centre satellite. This is a first for the country, with India-built AI models running on an India-built satellite and both training and inference happening directly in orbit, without any dependence on foreign cloud or ground infrastructure.

A useful pattern - use several agent sessions [say A1...AN] to research/implement/debug a feature(s) - get a showboat (agent's task specific proof of work) per session - ask another agent to integrate all this to the main pipeline/workflow - work with A1...AN to make sure their work is properly integrated - this gives them more "final use case" context. Also gives them context on how their feature integrates with other incoming features I unlocked insights that I couldn't see when working with each individual agent. Showboats are a game-chaning concept from @simonw simonwillison.net/2026/Feb/10/sh…

Yo blr people. Me and my friends are looking for a 3BHK apartment near Indiranagar, Domlur, HAL Road area Ideally some place - in a society with gym and pool (imagine that) - not in a noisy environment - cat friendly If you are moving out of a nice place or know someone who is, do tell Pls help @fmrbangalore @GruhamBot @BangaloreRoomi

overcooking you've seen this: someone ships a dashboard that shows every number with a sparkline, every action has a confirmation modal, every empty state has an animated illustration and a tagline. individually each decision made sense to someone. together it feels like chaos. nothing is in focus. that's overcooking. not one bad decision in isolation, but the accumulation of reasonable ones that no one said no to. AI makes this worse as the cost of adding dropped to near zero. it can build a feature, even a whole new concept in minutes. so people do. and then they do it again. the thing that started with a clear purpose slowly becomes a collection of additions that are each justifiable but collectively incoherent. the root problem is that most "new ideas" aren't new. they're repackaging of something that already exists at a more fundamental level. a new sticker on an old concept. it feels like progress because something changed, with a new word and skin – but the thinking didn't go deeper, it just duplicated itself into confusion. the whole has a core. you feel it once you understand the whole system. everything in it are related and balanced. when you overload it, that gravity weakens. not because any one thing is wrong – but because attention is finite and you force it everywhere. what we need aren't more tools that make more slop. it's seeing through the chaos, and returning to what the thing actually is, and cutting everything that doesn't serve that. that's harder now, not easier. because there's always something else you could add with one more prompt.

@CherryYadvendu @BangaloreRoomi @fmrbangalore yo ! this looks super cool. DM'ed you for more details

🌿 Looking for a flatmate | 3BHK in Domlur, Bangalore 🏠 Opposite EGL, fully furnished Rent: ₹25,000/month Cook — ₹3K/month House help — ₹1667/month 👥 Current: 1M + 1F | Female preferred, open to all @BangaloreRoomi @fmrbangalore

Looked into it. The approach is all reactive (hooks throughout the lifecycle, terminal bells). But : - have to write different hooks per harness - crucially, the agent never "knows" it's notifying you. - lots of "false positives" as you are just guessing when the agent might need you what if the agent can speak() ?

Humans invented git for human collaboration reasons. It’s increasingly clear that Git-based workflows may not be suitable once we remove the human bottleneck from the flow of code.

I work with a lot of agent harnesses simultaneously. And naturally go deep in one of the sessions (or drift away from all of them) they finish tasks or wait for my input or hit a snag. I reply to them a lot later than I "should" have. This is like you working with your most capable engineers in the same room and they just never tap on your shoulder. they just wait.

the hardest thing in my day to day workflow is getting everyone on the same page. On both these fronts - getting agents and me on the same page and - extend to getting me, agents and other humans on the same page.

@drummatick cli ftw. Any good MCP can be made a better cli tool

At what point does a tool become an MCP server? And what do modern agent harness like hermes or claude code prefer? Tools or MCPs?

@badlogicgames A simplification. Could be any feature that you (and pi) are not confident that they have the full picture. Take "creating animations like 3b1b" for example

@kumarsh0 the first question should be: why do i need a gh extension at all?

as more and more people start using pi, i now get this question often: "what are essential extensions i should install?" none. zero. start vanilla. only build/install something if you feel a recuring pain that you can't get rid of by reevaluating your workflow learned with another harness. i have 2 extensions: - promot-url-widget.ts in pi-mono/.pi/extensions: if a git issue/pr url is mentioned in a user message, it displays a little widget above the editor with the issue/pr title, submitter account id, and link to cmd+click. if i have multiple sessions open i know immediately what it's about - pi-diff-viewer, simple slash command spawning a GUI that lets me annotate a diff or any file in the working directory. once done, annotations are feed back to pi as a prompt, with a request for the model to act on the annotations. this is all i ever use. no, i don't use web search, mcp, multi-agents, whatever. i'm likely still outperforming you productivity wise with less token usage.

Literally me. collaboration should no longer mean "you can take care of features X and Y, while I will get the infra running and you can benchmark and test while he completes the frontend integration" This is all one person's job. If you understand it end to end, you implement it end to end. Period Collaboration between humans makes sense when your own e2e understanding falls short or you wanna enrich it by arguing with other teammates

The most efficient way for humans to collaborate: do not collaborate One person should own something end-to-end and work with agents

Let's say I feel the need of a github extension for pi. Me and pi decide that we wanna make it. We are aligned on goals. Now we want to know - what all should a good and functional github extension must have ? (objectifying/planning) - how are other similar extensions made these days (implementation) How do you get these without web search ? For context: I find claude's "Let me search how the community solves this problem" approach and follow up really helpful for these situations. Automatically enriches it's understanding

@kumarsh0 i have no idea what any of what you wrote means. give me a concrete example and i tell you how i do it.

i really want to people to understand that developer life is not a pokemon game. you do, in fact, not have to catch them all.

Personally I don’t see the point of Cowork. I don’t even see the point of chatgpt or Claude anymore. I either want to talk to a claw (agent with all my skills running on a persistent computer with NO guardrails in iMessage or telegram) or i want to use Claude Code or Codex app for coding.