Krunal Shah

Am out for a wedding to NY (unfortunate timing with launch) But Delegate has got me covered.

This is an amazingly powerful and capable product. 1. proactive 2. personal 3. great at web research (open and logged in context) Prepare to be amazed. As I've been saying in the team, "Just talk to it", it's great with memory. Happy Delegating!

@trq212 I would like my Garmin data protected by the Google 2FA provided by Tailscale over a simple bearer token auth which could be silently leaked by my CC.

@trq212 I'm running a Garmin MCP server on a local Mac, accessible only over a private Tailscale network. I'd love for both iOS Claude and browser Claude to be able to reach it — but without exposing it to the public internet.

Sorry @trq212 tagging you since I really want this feature and you seem really responsive. Is there any path toward Claude supporting MCP connections that originate client-side (app/browser) rather than from Anthropic's servers? That would make private network setups possible.

Okay what is going on with codex limits today? I know the 2x ran out today but this feels much worse than half.

This has been magical, especially combined with the power of Scouts’ recurrence.

Plus now Scouts can access your Slack, Notion, Linear, etc. Google apps and Granola coming next!

Memory is a wonderful feature. Claude is especially good at it. “Given your interest in Pinker, you’d probably enjoy it — Pinker draws heavily on Dawkins’s framework.​​​​​​​​​​​​​​​​“

Jed: My children choose morons, every one. Debbie: They say daughters look for their fathers. 😂

Scouts for iOS is live on Product Hunt! If you're active on PH, we'd love to hear what you think. producthunt.com/products/scout…

My demands have far crossed the limit of the current models. Yearning hard for the next gen of models trained on the multitude of data generated since Dec '25.

It's cute that both Claude and Codex estimate software development effort in human days. "Feature A should take 0.5-1 days; Feature B is 2-4 days of work" Me: well, not for you.

@nickhistgeek Valid point. What kinds of examples would you like to see? You can also try it out for yourself at yutori.com/api!

4-5x cheaper and faster is no joke. Edge cases though - that's usually where browser agents fall apart. Curious how it handles the messy stuff.

N1 is still SOTA on browser use. Give it a try!

You can now run @yutori_ai’s browser-use model (n1) on @usekernel's browser infra with a single line. Thank you for the partnership team!

@ehsanik @LucaWeihs @Vercept_ai @AnthropicAI Congratulations!

This is a long post, mainly because I have a lot to say, but in case you are too busy: TLDR: @Vercept_ai is joining @AnthropicAI! We shared a mission, so we joined forces to accelerate it into reality. Couldn't be more excited! Why Vercept was started In 2024, AI coding tools were already becoming magical for developers, but other industries were ages behind. It felt insane that when my mom had IT issues, I still had to hop on a call and walk her through it step by step. Insane that sending a simple email took so many clicks. That's why we started @Vercept_ai : Build something that acts for users instead of telling them how to do it. Two goals: 1) help people do tasks they didn't know how to do, and 2) handle the zero-brainpower tasks so people spend more time on creative work. As simple as scheduling meetings, as complex as reconciling messy financials before tax season. Ultimate goal was to have people spend less time behind screens and more time walking in nature. (Very Pacific Northwest mission 😁) The ride The journey of building an AI native company in this day and age was wild. Going from researcher to founder meant trading “reviewer number 2” for business partners and users, but surprisingly a lot of the same paradigms applied. Come up with a hypothesis, design an experiment, analyze user behavior, change the model and product based on the findings, wash, rinse and repeat. There are some differences though. The pace and the adrenaline. Lows are low, highs are high. We were constantly being challenged and learned at a pace we had never learned before. NEVER! If you are an adrenaline junkie like we are, it's a blast. The joy of the startup adrenaline rush is truly underrated. Why Anthropic We raised more than $50M, had a comfortable runway and a successful product, were building full steam with a small team, and were truly enjoying every minute of it. But that's when the opportunity came to join forces with Anthropic. We already knew how great Anthropic was at building models and we admired their mission, but then we learned more about the vision. We went on hours of walks, had long conversations, talked to members across different orgs, and learned more about Anthropic's vision and commitment to core beliefs which were very similar to ours. The more we talked, the more we realized we had been working on the same mission but from complementary perspectives. We realized that joining forces meant we could build something much much bigger together. And beyond the mission, I am now a big believer that Anthropic's real moat isn't its best model. It's the people. Incredibly talented folks who genuinely care about mission and real impact over hype. A zero-ego culture obsessed with building something meaningful. The choices were clear: we could build independently and work toward the same vision as two separate versions of it, or join forces with an incredible team and accelerate that vision into reality. The decision became an easy choice. What's next for our mission Mission continues, just got a bigger stage and an expanded team. The goal is still to expand AI beyond just a chatbot, to enable non-technical users to leverage it just as much as technical ones. We're just getting started. It takes a village This journey wouldn't have happened without the people who made it what it was. First and foremost, my cofounders @LucaWeihs and @inkynumbers . Best people I could've wished for as cofounders. We never once got into an argument, always had communicative discussions and as a cherry on top shared the same sense of humor! I feel blessed and grateful to have these two in my life. Thankful to our team for trusting in the three of us and showing up day and night. Grateful for @sethbannon , our board member, lead investor, great mentor and the person whose energy is so infectious that whenever we were having a down moment we would say "channel your inner @fiftyyears energy!" And to our wonderful investors and supporters: @chrija and @PointNineCap , Yifan and Jacob and @ai2incubator , and @mattmcilwain and Ted Kummert from @MadronaVentures . Couldn't have done this without you. Onward 🐜

I’ve personally subscribed to the more bearish predictions since I believe a. policy changes would be absolutely essential but not timely enough b. corporations aren’t incentivised to account for public good. But this is the most convincing bull case I’ve read yet.

@thesubhashk This is bonkers. You cannot tell me you don’t value interp research after looking at this.

My favorite analysis involved using AOs to measure Opus 4.6’s unverbalized eval awareness. On our blackmail eval, we found that 1) Opus latently reasons about being in an eval without verbalizing it 2) Steering against eval awareness reduces but doesn't eliminate awareness

We recently released a paper on Activation Oracles (AOs), a technique for training LLMs to explain their own neural activations in natural language. We piloted a variant of AOs during the Claude Opus 4.6 alignment audit. We thought they were surprisingly useful! 🧵