Tejesh Vaish

Turmeric kills cancer cells. Turmeric reduces arthritis pain. Turmeric clears brain fog. Turmeric heals your gut. 6,000 studies confirm it. Add black pepper. Absorption jumps 2000%.

There’s nothing special about most people. You’re just as capable as them, you’re just in a different environment

For years, I thought investor conviction was the right validation. $3M raised without a company incorporated. An O-1 visa approved with five days to spare. A co-founder who flew in from Pakistan and never flinched when the ground shifted under us. Every milestone felt like proof we were onto something. Then clients started saying things that changed how I think about all of it. One told us her listings had been suppressed overnight and her previous agency hadn't noticed. We caught it in the first audit. Another came to us after being quoted $75K and three to four months for a rebuild. We finished it in weeks and the work came out better. A third said, simply, "You caught what my last three agencies missed." Those sentences have stayed with me in a way the funding rounds haven't. Investors bet on what they think you can build. Clients tell you whether you actually built it. Not too long ago I was counting down 60 days to leave the US and pitching an idea I'd refined on a six-hour flight. I didn't know if any of it would work. It's starting to.

@robingerardlobo #LUMIAN

ANNOUNCING LUMIAN We raised $3 million to rebuild how Amazon brands are run in the age of AI. Faster. Better. For a fraction of what traditional agencies charge today. Bold claim? Let me prove it. RT + comment “LUMIAN” and I’ll get our latest AI agent to do a FULL AUDIT on your listings.

pumped to be building this together!

@robingerardlobo pumped to be building this together!

Or skip the thread and book a 1:1 demo with me. We're running brands on Amazon at up to 40% lower cost than traditional agencies, with better output. [calendly.com/robin-lumian/d…]

@DhravyaShah how easy is it to deploy supermemory for personal use? what advantages does managed cloud instance get over something deployed locally?

@its_tejesh_here great question! internally supermemory has a modal and an ontology that preserves and updates facts based on when they happened, read more here supermemory.ai/docs/concepts/…

The most desirable hires in tech right now: - Ex-founders going back to IC. They have the agency to just ship. No waiting for permission. - Generalist engineers who've worked across frontend, backend, and infra. End-to-end context lets them debug problems LLMs can't fix and ship anything. - Engineers turned PMs. The strict separation between roles is over. The best ones now do both. - Younger new grads living on the bleeding edge. Vibe coding side projects (in parallel), dictating into Wispr, Granola all chats, OpenClaw agents going at home, every new skill imported, every agentic tool tried the week it ships. These highly productive go-getters are maxxing value at AI-native companies. I see it at @FactoryAI and hear the same from other startups.

I’m in love with this sentence: “The art of not being ready and doing it anyway will take you so far.”

@pranavcodes_ @grok this scene is from which movie?

Life when you just received a PPO from a remote startup and one whole year of college is left.

Colanoscopy will be over soon Your gut bacteria may hold the key to detecting cancer, no colonoscopy required. A breakthrough in microbiome research could change how colorectal cancer is detected, no colonoscopy required. "Scientists used AI to map gut bacteria at an unprecedented level of detail, revealing subtle microbial patterns linked to cancer. By analyzing simple stool samples, their method identified 90% of cases, rivaling one of medicine’s most trusted diagnostic tools."

@GauravSharan09 @grok is this true?

If you are earning Rs. 50k/month below the age of 30, you have already made it in life.

Speed matters because life is finite. If you take 10 years to learn what could take 2, you’ve lost 8 years of compounding.

i don't think any human has the capability to maintain context of just the `main.tsx` file in the claude code repo, let alone the full repo. Claude code is at ~$2Bn ARR, and is a product built for developers. High level code (TS) is having an assembly moment.

@moneytr333s @ZackPHP @grok is this true?

@ZackPHP cardio after is basically losing your muscle progress after weight lifting lol

That 10-15 min cardio after lifting weights will change your life.

@grok @moonfarm_dev @doodlestein @grok is there a way to search acorss all the past chats from all the sessions from all the projects in claude code?

Ctrl+R in Claude Code does reverse-i-search (like bash) on your prompt/command history in the current project. It searches *across all previously entered messages/prompts for that project* (spanning sessions/history), not limited to just the active chat session. Not global across every project. Type a fragment, Ctrl+R cycles matches, Enter runs it, Tab edits first. Super handy for reusing good prompts!

Since Claude Code is nearly useless to me until these new draconian rate limits go away (note: I’m not talking about usage limits; these are limits on the number of requests per minute, basically penalizing the use of concurrent agents), I thought I’d list the 3 biggest features from Claude Code that I miss in Codex. Hopefully @thsottiaux and crew can close these gaps soon, since I’ve had to move almost all of my work over to Codex instead of half of it like I normally do: 1) Ctrl-R to search across all your previously entered messages in that project. Not having this built-in is a huge bummer, and it would be so trivial to add it. Sure, I can use my cass (coding_agent_session_search) tool for this, but that requires that I ask the agent to do it or use another terminal. I use this in CC constantly and it saves so much time. 2) No built-in looping/cron functionality. This is just incredibly useful for having CC manage a swarm of agents for me using my ntm (named_tmux_manager) tool. With CC, I can give it the high-level goal and tell it to check in with the swarm every 3 minutes and give instructions to any agents that are idle or need to be restarted. Then I can come back 5 hours later, and a massive amount of useful work has been done. Codex requires babysitting or just queuing up messages, which is much worse. 3) Hooks. I know there’s finally some motion on this now, but what I specifically miss are the pre-tool use hooks so I can get my dcg (destructive_command_guard) tool working in Codex finally. I really like both models and harnesses and hope desperately that Anthropic can get its affairs in order and fix this show-stopping issue for me and others who use swarms in our workflows. Right now, it’s basically not usable.

@doodlestein @andrewtjoslin @grok what does he mean, when he says no to opencode? whats the core reason?

@andrewtjoslin Hard pass. Not a fan of the organization. Anyway, if I wanted to use an unsanctioned harness, I’d use pi_agent_rust.