Chris Chabot (@chabotc) header
Chris Chabot (@chabotc) profile picture

MTS at @igent_ai clobbering agents over the head until they’re smarter

London, UK
Joined May 2008
Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)Photo by Chris Chabot (@chabotc)
Replying to @EmilyKager
Is that a null pointer? No it’s my nihilistic soul pointing at the void
3
40
This is such a big event. No but seriously, in an mcp and agent oriented world this adds lots of event driven use cases
The MCP Events extension is now finalised in beta. This means it is ready for clients and servers to adopt and provide feedback, so that we can fix any spec issues and get it stabilised. modelcontextprotocol.io/exte… Thanks to all the working group members, maintainers, and early implementers for getting this over the line. Very excited to see what people build with it :-) (and here's a cheesy video that on one asked for)
1
63
Did it first sit through all the mandatory HR trainings? How did it score? This has new benchmark potential
Microsoft’s Autopilot is built on OpenClaw, and it’s now rolling out in preview to eligible Frontier customers. Pretty damn cool to see what people are building on OpenClaw, and even cooler to see improvements coming back upstream. 🦞
71
It mirrors my own journey. My approach today is to create user journeys for every interaction and feature, measuring outcomes as the way to verify the correctness of work Anything not verified ends up having issues, and unit tests replicate the code in a different accent
Thoughts after talking to lots of engineers in London in last couple of days: • Everyone's moving into the same direction and getting more and more agent-pilled, but all on individual speed. No group of engineers right now is uniformly agent-pilled. • Becoming agent-pilled is a one-way door. You only realize this once you've gone through. Many think they "get it" but haven't made the switch yet. • Wild how many orgs are still treating agents as "thing that writes code on my computer" instead of robot-engineer that can help with whole SLDC. • Teams are drowning in PRs and code review. No process has been changed yet, even though this is the biggest dev productivity lever of last 30 years, engs still work off tickets like nothing happened. Wild. • Barely anyone realized yet that, hey, even if the model isn't good enough to write the code the way you'd write it [doubt it], they can surely write all of the peripheral tooling to speed you up. • Very few engineers have imagination to come up with better tool. Instead of reviewing code in diffs, line by line, think: if I could wave a magic wand and make tooling disappear, what tooling would I want to gain confidence in this change being correct? Full instrumented/traced end-to-end runthrough? Demo videos? In-production probes? High-fidelity and anonymized production data fed through test runs? New testing environments with the greatest debugging MCP support one can imagine so agent can inspect everything? It's time to dream big. But seems like most people's dreams don't reach further than "this agent works off the tickets assigned to me 10x faster than I can."
1
63
This is so good. Finding PMF and expanding markets is so much easier if you understand what your users want Might be a nice way to orient yourself on the “People don’t want a 1/4 drill, they want a 1/4 hole”
We messed up. We built an AI PM, but nobody wants another agent. They want to use their own. So we rebuilt the platform. Introducing Modem 2.0: finds problems buried in customer channels, tracks them, and follows up when fixes ship. Works with the agents you use every day.
1
54
I think the open button thing was started by Duke Edward VIII, so it seems only right that a king might change it back again
チャールズ国王がスーツマナー界隈を潰しにきた
1
519
This is the new shape of protocols, moving at agent speeds and aimed at enabling agents. It’s an agent eats agent world out there folks
Today we’re releasing Personal Agent Protocol (Poppy) v1.0. It’s on for everyone who uses Muse, @Meta's AI agent, enabled for every merchant on @Shopify, and backed by more than 100 design partners.
62
Chris Chabot retweeted
Hiring managers for my @OpenAI Startups Applied AI team, across Europe 🇪🇺 (London, Paris, Munich, Berlin) You'll run a team filled with ex-founder/CTO, research eng, MLEs. They're awesome, so you should care as much about people + culture as high performance. Details ⬇️
23
12
4
189
17,941
We’ve been testing this and it’s obviously a very strong model and a leap forward. What I personally enjoyed the most is that it’s better at writing as well
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.
50
That checks out. Peaceful, non cluttered. Books over tv. And a cat perch. Not bad
🤖 Made with AI
That checks out. "Design this room based on what you know about me"
1
93
Well that’s another attack vector to have nightmares about now ..
Video tampering can mislead every frontier model we tested into harmful actions, including a 100% attempt rate on stabbing a baby doll, producing toxic gas, and pouring water into a toaster. We're presenting at CoRL Late Breaking Results next week. 🧵 You Can't See Everything: Perceptual Attacks on Embodied AI
1
70
Blood for the blood god, skills for the skill throne next @kitlangton ?
I’m making a programming language called blood. Faster than rust, a powerful type system, all the power of effect systems, metaprogramming, zero-cost worktrees, semantic merging, sqlite-stored content-addressable code. Psychosis? Hopefully not. blood-lang.org
1
159
GTA VII is going to be wild
Replying to @yuchenping
Even a world? This started as a quick experiment: a small alley in Taipei as the starting image, and the same Atmee v2 model generating the scene continuously, live and controllable. There are still distortions and artifacts, but for a live avatar model it hints at where we’re going: an Agentic World Model, a world with life-like agents that behave like people. After all, what’s a world without the people in it?
77
Great opportunity for someone who is good at speaking with developers
105
“You get what you inspect” also applies to agents. Every tiny feature I didn’t build verification’s for ended up having subtle issues
3
10
25,209
Its like the scientific method: define your hypothesis beforehand or you’ll end up creating one after the fact that fits the outcomes
“Define "verified" upfront, because post-facto, you'll rationalize any outcome. “ It’s hard to understate how true these words from Addy are. Without strong verification tooling it’s impossible to fully trust agents. However it’s easy to fall into if you are not careful
97
My fashion trend prediction is that we’ll see a lot more scarves in ~eight weeks
really dislike a lot of menswear trend reporting. "corduroy is making a comeback." "the humble cardigan is suddenly everywhere." "this season, it's all about layering." "brown is having a moment." yea man it's called fall/ winter clothing and it's getting cold
105
It’s always been the rule in security: it’s impossible to make something 100% secure, you can only make it hard enough to break that it’s not worth it AI has changed the math of what effort it takes substantially
From a security engineer, on the AI threat landscape: "I actually don't think it's right that defense is going to get a lot harder because of AI. Most of these breaches, if there's already a security program in place at all that follows the kind of things that companies claim to be doing in SOC 2s or in other certifications, will provide the defense in depth to prevent these breaches from having any meaningful impact on their environments." I hate to say it, but Binance had every single on of these certifications, and got popped open, attackers stealing the largest-ever sum, $6B. I don't think the "traditional" secutity industry realized how bad things are. SOC2 does not protect you from zero days (that abliterated AI agents can and do find), nor from abliterated AI agents getting inside your trust boundary. In a few years I'm sure we'll have the certifications that mandate how to continioulsy scan your own systems with (abliterated?) models, red-teaming; and continiously monitor your live metrics (to spot anythig suspicious); and have near-realtime patching of CVEs (also surely with AI); and that MIGHT be enough But it's putting your hand in the sand assuming that pre-AI security posture will work just fine... unless it's secutity posture that is formally proven to work (see: cryptography)
2
1
3
243
Chris Chabot retweeted
Day 25/ We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today. We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage. And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
7,363
2,700
3,648
39,115
7,586,076