rahul (@CryogenicPlanet) header
rahul (@CryogenicPlanet) profile picture

leadership @composio; prev founded @scalardotvideo; e/acc

hayes valley
Joined March 2020
Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)Photo by rahul (@CryogenicPlanet)
who knew building a self driving cars was easier than automatic closing doors
2
11
872
even before they announced they we’re sunsetting i was playing with decompiling arc removing the account and internet features was super easy, working on fully separating ArcCore from chromium version so it can have easy security updates (agents are almost done on this too) github.com/CryogenicPlanet/a…
7
7
3
161
16,724
i really feel for the @opencode and @Railway teams it’s easy to make fun from outside and likely were some real mistakes but with the model cyber capabilities not really anyone’s fault and these attacks are absolutely hell i didn’t sleep for 4-5 days in may, had multiple agents running sweeps the entire time i understand the comms haven’t been good from them but also these attacks are much more sophisticated than you can imagine
Replying to @Railway
i'm sure you're all better than me at this but just some of what we've seen if it helps - they're not going to stop. it's going to get increasingly sophisticated and they're going to go after every surface of your system and all of your employees any old projects you've long forgotten about will be found and used against you the only reason we're surviving is because we have agents going 24/7. we're still barely sleeping good luck, sorry you're dealing with this, but really it's a collective problem we're all facing together
6
1
2
126
39,210
watching rahul build this has been so incredibly impressive and inspiring very cool to see them succeed
1
1
23
1,558
somehow the new issue of @WorksInProgMag is even better done than the past issues holy shit didn’t think that was possible
3
5
29
3,406
half baked idea but would love it if github let my agents auth sorta as me (they can do most things i can do) but other agents and me can know which agent did what @claude merged this or @bot merged that or said that or whatever vs always as me you can sorta hack this but a lot of work
1
290
one of the things i’ve seen under discussed before is just how chinese open weight models even on american hardware can either be sleeper agents and/or just write zero day vulnerabilities into code and there would be very few ways to detect this open weight models are def cool but like i always found the if they just run on american hardware everything is safe argument very weird
We are approaching cyber-superintelligence. But our systems aren't ready. We must secure our model weights and infrastructure against three new threats: sabotage, escape, and theft. There is a way forward. Secure Acceleration: A Cyberdefense Strategy for Superintelligence
1
2
11
2,357
i've been loving instinct but i find that i jump between a lot of agents, rn mostly claude code, codex and instinct lots of context is lost between them, very often i want to start something on cc then handoff loop to instinct, etc been hacking on chirp.wiki to solve this
7
6
1
36
1,914
chirp is super simple, fully oss agentic message board has some basic primitives and then fully extendable very inspired by @pidotdev a running chirp board can be live edited by any of its connected agents to add/change functionality without redeploys github.com/CryogenicPlanet/c…
6
303
i’ve been loving instinct and not been really using it for work (yet) i’ve been traveling in istanbul and the ease of doing this, drop a pin find me food or whatever is just so good plus like book hotels, tour, reschedule them etc and just handle the comms back and forth
I’ve really been enjoying Instinct, a personal AI agent. The simplest description for it is: OpenClaw for normal people. It feels like magic. And contrary to what some people have said, I don’t think the appeal is limited to Silicon Valley types, we are setting my dad up with it too. I’ve exchanged 677 messages with Instinct in the past five days. Here are some of the things it has done for me: 1) I asked who I should see about fixing my flat feet. It recommended starting with a podiatrist, found a well-reviewed one who takes my insurance, and filled out all the paperwork for me. I HATE finding in-network doctors, so this is a great use case for me. 2) It helped decrease my Comcast bill from $100/month to $60/month. It hit a wall on this one but gave me a number to call and an exact script. The call took three minutes. 3) We’re ordering custom merch for my brother’s wedding. It found vendors and is messaging several of them on WhatsApp- asking questions, comparing options, and negotiating prices while I’m asleep because the vendors are in India. 4) I’m planning his bachelor party. Everyone posted their arrival details in a WhatsApp group, so I asked Instinct to organize everything in a spreadsheet. It has access to my WhatsApp, so there was nothing for me to copy and paste. 5) My wife and I are going a wellness retreat (Miraval) in a couple of weeks, where many of the activities need to be booked in advance. After some back-and-forth about what we’d enjoy, Instinct researched the highest-rated activities and booked them for us. Massage slots appeared to be unavailable online, so it emailed the hotel from my account, found times that worked for us, and booked those too. 6) It did something similar for a girls’ trip my wife is taking with a friend, but booked very different activities for the two of them than it did for us. 7) It booked a DMV appointment for my new driver’s license. 8) It canceled all my Amazon Subscribe & Save subscriptions. 9) It activated all the free offers on my credit cards, just in case. I can't be bothered with those but if it's no work on my end there is no harm 10) It price-shopped my car insurance and concluded that I already have the best rate through Tesla. 11) My wife and I are traveling on the same United flight but booked on separate tickets. Instinct contacted United and linked our itineraries, a task that requires chatting with the airline and can’t be done through self-service. 12) It found and booked a factory tour at an Amazon fulfillment center that I'd been meaning to do, at a time that fit my calendar. 13) It suggested topics for a podcast I was appearing on. I didn’t end up using all of them, but they were pretty good. 14) It reminded me about a bunch of unused gift cards I had forgotten about. 15) I sent it a photo of a toll notice. It paid the toll, discovered another outstanding one, and paid that too. None of these things is individually life-changing. Some of these things can be done via their own apps... But together, they represent hours of annoying life admin I didn’t have to do, and I have one easy place (imessage!) to do them. There’s an obvious question: why doesn’t ChatGPT, or, Meta or Google already do all of this? The underlying technology clearly exists- to use tools and complete multi-step tasks. But they haven't packaged it as a persistent personal operator with this level of access to your accounts and communications. The other AI's are also more cautious about purchases, cancellations, messages, and other external actions, so they will often stop for confirmation, which kills the vibe tbh! Note: I haven't been playing with Grok Bot yet, which I think does a lot of this. A year ago I thought memory was the killer feature and it was awesome that ChatGPT had it, but Meta and Google had even more context / a natural advantage that they could ride on to be your personal AI agent. Meta's data with WhatsApp, etc...; Google with Gmail, Calendar, Chrome, and Android. But I've found the data that Instinct gets from being connected to your email to be pretty sufficient to get started and it can fill in the gaps. And the amount of context Google/Meta have that could make their assistants incredibly useful would also create enormous privacy, compliance, and trust problems for them. Plenty of people are uncomfortable giving those companies this much visibility into their lives, lawyers and lawmakers would come after them like crazy... not to mention there are probably all sorts of T&C's that Instinct is breaking. It is a bit scary how much information Instinct has and what it can do. We're going to start to see a new excuse: "I didn't send that email, it was my AI assistant" Anyway, good opening for Instinct. Much less about having a uniquely capable model and more about the product harness around it: integrations, permissions, context, persistence, willingness to keep working until the task is finished. Something like: ChatGPT/Claude still feel like assistants that you operate, but Instinct is an assistant you employ. Very cool product. It has the potential to make life easier for a lot of people. Excited to see more develop here. And if you want to sign up go here: app.instinct.co/ currently on waitlist. I don't have any more invites. I gave out 100+ invites on here and they were taken in 2 mins. If I get more I'll post them!
2
11
1,569
Lulu (@lulumeservey) is the best in the world at what she does. She’s the go-to comms strategist for Silicon Valley and many of the top founders in tech trust her. She’s an advocate for going direct, has built a singular career and shares everything she’s learned. 0:00 From China to America 2:08 Learning to Read the Room 6:18 Building a Movement 7:30 Learning Comms by Doing 10:50 Anduril as an Insurgent 15:07 The Power of a Manifesto 18:47 Go Direct 26:45 Conviction Over Charisma 31:30 Why Rostra Exists 33:23 How AI Leaders Lose Trust 40:40 Tell a Better Story 47:55 Do Things That Can't Be Faked 50:55 The Return to Beauty 57:11 Originality Over Templates 1:04:02 Do What Only You Can Do 1:07:14 The Jetsons Rule 1:10:41 Trust Yourself 1:12:29 Why Humans Crave Stories Includes paid partnerships.
92
136
71
1,652
1,035,867
it was inevitable some point i would become a podcast bro
The first company I ever joined was @rubrikInc, @Jainarvind's previous company. It's where I learned how to build systems and engineering teams. Years later, when we started @composio, @glean became one of our first customers, one of the first to believe in what we were building. So sitting down with Arvind felt like closing a loop. In this episode: •How Glean brought transformers to enterprise search before "semantic search" had a name •Glean's partner-first strategy and why they chose Composio for actions •Why Arvind has never worried about competing with OpenAI or Anthropic •GLM 5.2 as the open-source inflection: 90%+ of enterprise AI tasks, majority of inference within 12–18 months •Measuring real ROI: the US telco that cut case-resolution time by 48% •Why agents built on MCP alone act like day-one employees and how context graphs make them tenured CHAPTERS: (00:00) – Rubrik days: how Arvind and Karan met (01:05) – Glean's origin story: transformers before "generative AI" existed (03:04) – What Glean is today: superset of ChatGPT and Claude (05:39) – From embedding search to agents: was it a pivot? (11:39) – The Composio partnership and why actions are hard (14:43) – Why competition doesn't matter yet (20:11) – The open-source inflection point (GLM 5.2) (24:41) – Contracts and model risk: who absorbs the volatility? (26:57) – Enterprise ROI: cost, tokens, and what to measure (39:57) – Measuring value team by team (44:11) – Day-one employees vs. tenured agents (46:09) – Closing thoughts
3
11
1,468
powered by composio
The Quick desktop app is here, and it’s compelling. Connects to your email, calendar, Slack, local files, and several other apps to flag important communications, retrieve and summarize info, make recommendations, send communications, and create agents that do work you used to have to do yourself. Gets smarter and more personalized the more you use it. Been using it a lot recently and is changing how I work. It’s allowing me to use applications like my inbox more like an archive, and Quick as my personalized, prioritized, productivity hub that can multi-task various needs. Still early days, and a lot more coming, but excited for folks to start using it to make the undifferentiated work so much less complicated. aboutamazon.com/news/aws/ama…
1
2
17
4,176
when claude is actually composing with @composio
2
12
924
Let us handle the fun stuff (auth), and you can focus on boring things like building agents
Your AI agent is in bed with you. No protection. You just wanted it to work. Gmail. Allow. Calendar. Allow. Slack, Notion, GitHub. Allow. Allow. Allow. Every password, handed over. Your agent never needed a single one. They just needed @Composio Secure your agents in minutes ↓ composio.dev/protection
2
1
10
2,055
our cold emails while still cold emails are the best cold emails according to @itsaqd extensive benchmarking
Several of you had feedback about Jarvis. We listened. Today we're publishing the full evaluation: 94.2% on Spam-Recruiting-Email-Bench. 97.8% on LinkedIn-Bench. Jarvis has read your feedback too. It has added you to the pipeline.
1
7
784
one of my fav things in the new @composio cli is the run command. our cli is a @bunjavascript static binary so we just let it run JS code to execute against your tools. lots of cool uses but my fav is experimental_subAgent, spawns a local claude/codex session wiht ACP
Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck. So we hit the streets of SF to see if the city agreed. We posed a simple question: MCP or CLI? - Basically everyone under the age of 35 said CLI - One person said MCP was as bloated as Java - & unsurprisingly, numerous people told us to touch grass Final score- MCP: 3 vs CLI: 17 SF has spoken, and @composio listened. Our universal CLI is now live! Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀 Link to try our CLI in the next thread ⬇️
1
1
20
9,420
The universal CLI is here! Brilliant.
Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck. So we hit the streets of SF to see if the city agreed. We posed a simple question: MCP or CLI? - Basically everyone under the age of 35 said CLI - One person said MCP was as bloated as Java - & unsurprisingly, numerous people told us to touch grass Final score- MCP: 3 vs CLI: 17 SF has spoken, and @composio listened. Our universal CLI is now live! Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀 Link to try our CLI in the next thread ⬇️
14
5
44
28,315
first proper video i've edit in a while and got > 1M views maybe its time to return to video editing an insane hack here was claude code + remotion + prores alpha channel most of the effect and text in the video is just claude code
Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck. So we hit the streets of SF to see if the city agreed. We posed a simple question: MCP or CLI? - Basically everyone under the age of 35 said CLI - One person said MCP was as bloated as Java - & unsurprisingly, numerous people told us to touch grass Final score- MCP: 3 vs CLI: 17 SF has spoken, and @composio listened. Our universal CLI is now live! Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀 Link to try our CLI in the next thread ⬇️
5
1
26
2,280
team cli all the way!
Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck. So we hit the streets of SF to see if the city agreed. We posed a simple question: MCP or CLI? - Basically everyone under the age of 35 said CLI - One person said MCP was as bloated as Java - & unsurprisingly, numerous people told us to touch grass Final score- MCP: 3 vs CLI: 17 SF has spoken, and @composio listened. Our universal CLI is now live! Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀 Link to try our CLI in the next thread ⬇️
2
12
711