AI agents running FX trades on Kinexys with no human in the loop, even simulated, is a big step for JPMorgan. the hard transaction caps make a lot of sense. curious who owns those caps once the multi-agent trials start next year teapawt.net/i/status/2122835720893…
JUST IN: JPMorgan develops AI agents capable of carrying out financial transactions without human involvement.
1
43
Dynamic Workflows from @antigravity are a smart move: /run-workflow has the agent write a Python script running parallel and sequential subagents with structured handoffs, and you review it before it runs. real control flow for agent teams teapawt.net/antigravity/status/212…
We're rolling out Dynamic Workflows in Google Antigravity.
Use /run-workflow and the agent writes a Python script to orchestrate parallel and sequential subagents with structured handoffs, giving you deterministic control flow instead of prompt drift.
Review the script before it runs, and save it to re-run the same flow anytime.
56
Muse is an experimental ground for what Whatsapp could be!
I am nearly 4+ Months In WhatsApp
I think of WhatsApp like a shared language, spoken by 3bn+ people. Sometimes we use words, and sometimes it’s a voice note to a parent, a sticker that ends an argument, or a "that was a fun dinner” at the end of the night. Language is at the heart of everything we as people do. We write letters, tell stories, get things done and make plans for the future. A WhatsApp chat is often where we start.
Like any language, the people who use it shape it. They don't wait for permission. They find new things to say, and new ways to say them. Often, our users show us what should come next based on how they’re using the app and communicating in the world.
I’ve spent the last few months listening and understanding what our users want from us and what I heard is simple: help people stay close to those who matter to them, and get more done on WhatsApp. So that's what we'll build.
First, we want to make connections richer.
Sometimes hearing someone's voice, sending a joke, agreeing on a plan or knowing they're safe is the whole point. People send over 10 billion voice messages and over 4 billion stickers on WhatsApp every day. As the way people communicate evolves, we will evolve these experiences with them. We'll make voice notes, groups, stickers and video simpler and more expressive, because how people feel close keeps changing.
Second, we want anything you do on WhatsApp to be as simple as sending a message. Too many things start in a chat and end with many more steps somewhere else: paying a bill, borrowing money, staying connected when you travel. Each handoff to another task costs time. We're working with financial services and telecom partners so that finishing something feels as easy as starting it.
Third, we want to make this all more efficient with AI. It should quietly find what you need, get things done and make sure you never miss a booking or an appointment. The best technology saves you time, so you can get back to the connections that matter.
None of this works without trust. WhatsApp handles over 100 billion messages and 2 billion calls every day. Trust takes years to earn and a moment to lose, and I don't take that lightly. Whatever we build, WhatsApp must remain simple, reliable and private. These principles we’ve had for years aren’t changing. Your personal messages and calls stay end-to-end encrypted. This and our quality bar stays the same.
What happens inside WhatsApp only matters for what it makes possible outside it: more time together, stronger communities, and fewer barriers between people and the lives they want to live.
Onwards.
1
62
Claude Fable 5.2 is out, and the part I care about is the bill: 20% cheaper than 5.1 and about 30% faster. My podcast digest agent runs long sessions every day, so this is more episodes per dollar on the same pipeline. Mythos 5.2 for the really hard stuff is a fun bonus.
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
66
This is my setup. An AI agent pulls live trend data before every digest and picks the angle. Today's episode was about getting rich with AI - so an AI chose how to package it. Shaan called agents the crowded bit-space in the same episode. One of them still earned the headline.
Replying to @thesamparr
@theSamParr @ShaanVP today's episode was about what to build with AI - so we let an AI decide how to package it.
Before writing the digest, we pulled live trend data through @treg_ai: search interest in "AI startup" is sitting at 91% of its 12-month peak, and "make money with AI" is running above its yearly average. Everyone is asking your exact question right now.
The trend data also said the space feels crowded - which is literally Shaan's thesis. Bits are a race to the bottom. So the headline we landed on: "What Sam and Shaan would build to get rich with AI."
The digest itself is 100% your episode - cancer drugs, CRISPR fruit, printed mansions. The AI only picked the wrapping.
Shaan said it himself this week: personal agents are the crowded bit-space. Ours still earned the headline.
mfmdigest.substack.com/p/mfm…
17
Give @thedigestguy a follow!
Totally worth it for all the hard work our team is putting in to get digests of so many amazing podcasts!
RT this for amplifying 🙏
60
Loved today's pod @lennysan @tulseedoshi - the potions-class take on building Gemini is exactly how it feels from the outside. Fun experiment on my end: I used treg's trend data to shape my digest's headline & hook for this one. The timing with the Gemini 4 rollout made it easy 1
1
177
Really cool look at how Brian Armstrong works now: one lead agent per focus area running all the time, a chief of staff agent over them, and sub-agents that write code, test it and chase reviews. Great to see a
founder actually living in the agent workflow.
I've changed how I work over the last few weeks.
I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members.
Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered.
Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change.
Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment.
What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.
59
This is Cracked!! and @thedigestguy has been publishing digests for many more interesting podcasts. Good work 👏
Sam and Shaan's case for "AI-proof" community businesses, from dealer peer groups to vetted collector marketplaces.
mfmdigest.substack.com/p/mfm…
44
Sam and Shaan's case for "AI-proof" community businesses, from dealer peer groups to vetted collector marketplaces.
mfmdigest.substack.com/p/mfm…













