If you want to try a new personal agent that is just… insanely good, comment + DM me.
@mattshumer_
-
Guided vulnerability detection differs from autonomous discovery
By
–
It's very cool work, but it's not 1:1. The report shows that they basically lead the models to the right spot for them to do the work. It's more "is this a vulnerability?" than "find a vulnerability". Mythos had to find it from scratch, these were told where it was.
-
Best Memory Systems for OpenClaw and Hermes Agent
By
–
What memory systems are people using for OpenClaw and Hermes Agent? What's the best thing available (ideally OSS, stable, and simple to use)?
→ View original post on X — @mattshumer_, 2026-04-03 19:37 UTC
-
AI Video Calls Becoming Ordinary with Pika’s Real-Time Model
By
–
We’re just a couple years away from video calls with AI agents feeling completely ordinary. https://t.co/7USlSrH161
— Matt Shumer (@mattshumer_) 3 avril 2026We’re just a couple years away from video calls with AI agents feeling completely ordinary. Pika (@pika_labs) Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0. The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅 — https://nitter.net/pika_labs/status/2039804583862796345#m
→ View original post on X — @mattshumer_, 2026-04-03 04:31 UTC
-
Anthropic’s New Claude Mythos Model Dramatically Surpasses Opus 4.6
By
–
This is absolutely crazy. Anthropic trained a model that is "dramatically" smarter than Claude Opus 4.6. Think about how good Opus already is. Can you even imagine what a far better model might be able to accomplish? The world is changing, and it's changing fast. Buckle up. M1 (@M1Astra) Claude Mythos Blog Post Saved before it was taken down. m1astra-mythos.pages.dev/ — https://nitter.net/M1Astra/status/2037377109472018444#m
→ View original post on X — @mattshumer_, 2026-03-27 19:11 UTC
-
Composio launches universal CLI, defeating MCPs in SF poll
By
–
The universal CLI is here!
— Matt Shumer (@mattshumer_) 27 mars 2026
Brilliant. https://t.co/r7yHT3CSaqThe universal CLI is here! Brilliant. Karan Vaidya (@KaranVaidya6) 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 ⬇️ — https://nitter.net/KaranVaidya6/status/2037530089706176638#m
→ View original post on X — @mattshumer_, 2026-03-27 17:38 UTC
-
ARC-AGI-3 benchmark released, frontier models underperform humans
By
–
1. Incredible.
— Matt Shumer (@mattshumer_) 25 mars 2026
2. I give it four months before this is ~saturated. https://t.co/u9dc9lIBgz1. Incredible. 2. I give it four months before this is ~saturated. François Chollet (@fchollet) ARC-AGI-3 is out now! We've designed the benchmark to evaluate agentic intelligence via interactive reasoning environments. Beating ARC-AGI-3 will be achieved when an AI system matches or exceeds human-level action efficiency on all environments, upon seeing them for the first time. We've done extensive human testing that shows 100% of these environments are solvable by humans, upon first contact, with no prior training and no instructions. Meanwhile, all frontier AI reasoning models do under 1% at this time. — https://nitter.net/fchollet/status/2036861192619384989#m
→ View original post on X — @mattshumer_, 2026-03-25 22:30 UTC
-
The Rapid Shift from Human Marketing to AI Agent Marketing
By
–
We are unprepared for how quickly the world is going to shift from marketing to people -> marketing to AI agents
→ View original post on X — @mattshumer_, 2026-03-25 20:32 UTC
-
Sam Altman on OpenAI’s Strategy: Data Advantage for Wrapper Startups
By
–
talked to a YC founder who asked Sam Altman straight up "will OpenAI compete in my space / kill my startup"
— Joseph Choi (@JosephKChoi) 25 mars 2026
the answer: behavioral health requires knowing if users are actually improving. OpenAI doesn't have that data, the wrapper startups do. v bullish for consumer AI pic.twitter.com/JYpMxEOhRbtalked to a YC founder who asked Sam Altman straight up "will OpenAI compete in my space / kill my startup" the answer: behavioral health requires knowing if users are actually improving. OpenAI doesn't have that data, the wrapper startups do. v bullish for consumer AI
→ View original post on X — @mattshumer_, 2026-03-25 18:19 UTC
-
Future UIs Will Stream from Cloud to Device Screens
By
–
In 5 to 7 years, UIs will be generated/streamed from the cloud, pixel-by-pixel. Phones/etc. will literally just be useless bricks with screens, speakers, and input. That said, UIs won't be as dynamic as people expect. Imagine a new UI each time… that'd be so hard to use!
→ View original post on X — @mattshumer_, 2026-03-25 18:00 UTC