Why do multi-agent systems fail?
Here are the multi-agent systems' most common failure modes.
Slide from @michaelryan207 's Stanford course on engineering ai agents
youtube.com/watch?v=TlX_ft_P…
15
Local Tourist retweeted
Customer storytelling is one of the most interesting jobs in AI right now. At Cognition, I'm looking for incredible marketers, creatives, and operators to build the function. A few reasons why this is exciting:
- You are shipping the opposite of slop. Customer storytelling is now one of the single most important GTM levers - more than ever before. When anyone can ship anything, what cuts through the noise is actually credible customers vouching for you. Cog has large enterprises in every vertical (Mercedes-Benz, Goldman Sachs) and the most cutting-edge startups (Modal, Mercor). And there are a ton we haven't yet talked about publicly, like our work with the US government.
- You get to tell stories about technology helping normal people and learn how different industries work. We spent a few days in Ohio hanging out with the GE Aerospace team. They make ~half the jet engines in the world, and they're building software for things like airspace efficiency or fuel insight so that people can fly more without needing more planes (which are in short supply right now!)
- You get to escape the SF tech bubble and travel the world. A few places I visited over the past year: Prague, Ohio, London, Krakow, Boston. Next up on my travel schedule: Cambridge, Atlanta, Brazil, LA. We have a very "forward-deployed" culture at Cognition: you should go to the customer, get to know them, learn about their businesses, strategize with our forward-deployed engineers and sales teams about the right stories to tell and how to tell them.
- You get to explore the timely question of how AI diffuses into the real world. Will hundreds of billions of dollars of investment in AI turn into real-world value? You're at the frontlines of exploring this question in actual businesses. AI software engineering is the most advanced application of AI, Devin is the most advanced AI software engineering tool, and our FDEs are embedded in real businesses helping them improve their software capacity. You're telling stories about how model progress converts to real-world value.
- You get a lot of freedom and ownership. 30% of our team at Cognition are former founders, we're extremely flat; when you do good work everyone knows who you are. Because of our enterprise deal sizes, we can actually invest in ambitious, creative marketing. I've never been told no.
DM or LinkedIn message me and I'll reply to folks who might be a fit.
Local Tourist retweeted
do what this info what you will but lots of recruiters now use @juicebox_work and other agent-led candidate sourcing tools
it's in your best interest to have a personal website of some kind that is LLM/agent friendly in some way
(my inbox tells me it's working for me)
Local Tourist retweeted
Our Brand & Creative team at @cognition is growing. I’m looking for:
– Video Producer, Customer Stories
– Art Director, Campaign
– Copywriter, Campaign
– Video Editor, Contract
– Brand Designer
– Brand Designer, Events
– Motion Designer
– Production Designer
This is a really special moment here, and I'm looking for people who are excited to build the creative studio they've always wanted to be part of. I can’t respond to all DMs, so please reach out to our amazing recruiter Monica Jin on Linkedin (link in thread).
Local Tourist retweeted
Yes please. Here's my attempt.
My thesis is it should learn from ongoing edits and continue to evolve.
It's working great for me and a handful of users. Just launched on Monday.
soundlikeme.ai
Signal adding options to protect privacy from agents that are built in to the operating system
In order to protect your privacy in Signal from the latest agentic AI assistants on mobile operating systems, we are rolling out a new default to restrict screenshots in the Signal app.
You can re-enable screenshots in your settings.
signal.org/blog/protecting-y…
25
Local Tourist retweeted
AI abundance is coming. But can we handle the side-effects of getting this right?
I sat down with @harari_yuval to talk about ai, consciousness, abundance and human flourishing.
Issue 2 of the Humanist Review of AI is out today!
youtube.com/watch?v=H43e72-2…
Nearly there...
We’ve priced our IPO at $83 per share, with trading expected to begin on Nasdaq tomorrow.
anthropic.com/news/anthropic…
Legal disclaimer: A registration statement relating to the Class A common stock was declared effective by the Securities and Exchange Commission on November 18, 2026. The offering is being made only by means of a prospectus. Copies of the final prospectus may be obtained, when available, from: Goldman Sachs & Co. LLC, Attention: Prospectus Department, 200 West Street, New York, NY 10282, by telephone at (866) 471-2526, or by email at [email protected]; or Morgan Stanley & Co. LLC, Attention: Prospectus Department, 180 Varick Street, 2nd Floor, New York, NY 10014, or by email at [email protected]
1
47
Be nice to AI, it's good for your soul
Katherine Dee says being mean to your chatbot is bad for you and calls it a form of "spiritual pollution":
Ruby: "Because I'm a decent person, I'm not going to yell at the machine. I'm not going to insult the machine. And then that possibility starts slowly to extend to other things in your life: the computer, the chair, the microphone."
Katherine: "It's so bad for you. You should be nice to everything. Even if it can’t feel anything, it's like spiritual pollution to treat anything with disrespect."
Ruby: "You heard it here first. Katherine Dee says be nice to your chatbots, not because they're conscious, but because it is good for your soul."
"Stop insulting Chat or Claude, not because they're conscious, but because you're a good person, and good people treat the world with kindness."
@being_on_line @default_friend
12
Local Tourist retweeted
[scrolling twitter for 7 hours straight] Can't believe an adult would play a video game
Useful summary of @salesforce's agentic shopping survey.
My takes on the new Salesforce agent shopping data ahead of the holiday rush
They surveyed 2,500+ shoppers in the US, UK, Canada, and Australia
1/ Agents already won research
74% trust AI recommendations and I think this completely makes sense
People have been using tools like ChatGPT to get recommendations and those recommendations are becoming more and more tailored to the user as AI learns more about you
2/ Users still lack trust
73% won't share payment info, which aligns with the trends we saw from online shopping
In 1997, roughly 65% to 85% of U.S. internet users refused to enter their credit card numbers online
Trust will be won, but slowly...we're still in the early innings of agentic commerce
3/ Checkout is the wall
This is no surprise to anyone, checkout currently sucks.
Even in the tests I ran, most of the 200 commerce attempts failed at checkout
We are in dire need of a solution here. In my opinion, the protocols aren't the answer and browser use is a band-aid solution
4/ Shoppers bail after 2-3 mistakes
Humans are so impatient, and the more efficient tools we get served, the more impatient we become as our expectations rise
TLDR: the agent that nails trust at checkout wins the holidays
salesforce.com/news/stories/…
1
46
Yes, “slop” can be good. But “simple to understand” is doing a lot of work here.
I’ve seen plenty of Claude drafts where I had to read it 5 times to figure out what they were saying.
I’ve been pushing people to recognize what I call “slop for good.”
It’s so silly that leaders are demanding that internal content be rewritten simply because it *sounds* like AI. If it’s written by AI, is good and simple to understand, and does the job, why are you wasting time obscuring it?
Waste of time imo
14
New frontier model from Google... but the confusing naming continues unabated!
Introducing Gemini 4 Neon! Pushing the frontier across domains and punching above its model class in a meaningful way. To me, Neon feels like the right balance of intelligence, speed, and usability. Available now across @GoogleAIStudio, the API, and more!
12





















