🥁 INTRODUCING: The How I AI Personal Agent Bench I test 4 agents against 9 tasks to figure out which really is the best. The results are in: 🏆 @bot (by A LOT) 🥈 @Muse 🥴 @ChatGPT Dot 🫠 @claudeai Duet Let the @poteto mogging begin Full ep on YT: piped.video/watch?v=hnCoQ5wB…

Wish I had discovered Banks and The Culture series in my teens, when it would have appealed to me. Clearly important text for understanding the builders of AI, but such a slog…

my tl;dr on claude duet +++ design - no notes, v mindful, v demure ++ onboarding - clean and easy ++ models are good + connects w my other stuff + artifacts on mobile, what a time to be alive + channel concept - good design, but not good use of personalization (i created a sales channel and it asked what the channel was for) -- SLOW -- I forgot it

🤖 ANOTHER ONE: @claudeai Duet launches in research preview + I add another personal agent to the stack. I tested it...then forgot it. Will this absolutely beautiful agent earn its place in my AI stack? My take now live on YT: piped.video/watch?v=HYb5w4Pf…

I could vibe code lots of personalized software for one off use cases, but Im realizing Im happy to pay for software built, QA'd, and maintained by someone else. Iterating through tiny edge cases with AI doesn't spark joy.

Gemini has a new model out and I have no desire to test it. It feels like we're at the iPhone 'S' stages of model releases, sure, they're better, but evolutionarily. Alignment nerds geeking out on CoT, though.

Just had a chance to host a chat with @emollick about his upcoming book, Co-Existence. It is going to be a hit and is full of practical insights on AI. There will be many positive reviews of the ideas, but let me suggest three non-obvious meta-reasons to read it sooner rather than later: 1. How to work (co-exist?) with AI. Every so often, Ethan pulls back the curtain and describes how he uses AI in the book writing process. You get a peek into specific techniques and, more importantly, the mindset that will make someone successful. 2. The Mollick production function. The book is long enough to give Ethan breathing room to show why he's such a different thinker and fun to hang out with. He actually plays with the tools for long enough to get a finger-feel for what's possible (that's why he is texting at 2 am!); he constantly conceptualizes what he's encountering (jagged frontier, leadership-crowd-lab, the multi-player 2x2, etc.), pushing the ideas to their logical (and often uncomfortable) conclusion; and he ruthlessly throws away ideas when they no longer match the facts on the ground (especially important as everything changes so rapidly). 3. Common knowledge. In this time of hyper-personalized bubbles, we forget the value in having a shared set of stories, frameworks, and ideas. Ethan's book is going to be read by everyone from CEOs to ambitious high schoolers. The book is going to be referenced at many business meetings and holiday dinners so you might as well join in the fun early so you can give a knowing look when someone tells his escalator vs eschaton story, explains the best reasons not to use AI, or debates StrongDM-style software factories.

imo one of the underhyped launches of @OpenAI dev day were all the rad updates to Sites, especially connected data + site-as-infra which is why it was so fun to sit down with @simpsoka (product lead) and talk about the practical + fun ways she uses sites. in this live ep we cover: - how sites can use your connected enterprise data + user permissions to create micro SaaS everyone can use - fun consumer use cases, like a Spotify playlist sans baby music - the internals of Sites + how it can host so much more than just webpages anyone struggling with "where the f do we deploy all these internal tools" should pay attention 👇 Full ep on YT: piped.video/kz5Cpomk3HA

The contrast between hanging up the last phone call of the day of high-stakes decisions and then a minute later walking in the door to the pure love of small children who want to laugh and play and show you every discovery they made that day is the strangest and best thing I have ever experienced in life.

🚨 side project alert 🚨 Announcing Muse Gadgets, an open source ESP32 firmware and Linux sdk so that you can make hardware devices that work with Muse. Grab an API token from gadgets.muse.ai and point your favorite coding agent at the github repo to build your own peripherals for Muse.

pls don’t make me roll up with my 3 sons and mog you on birth rate contribution

Jev week continues with one of our top returning guests, @johnlindquist, where he shows about a dozen different things you can build with this @typesafeai decision model. He shows: - multi step routing - deduplicating messy data - model v model blitz chess - a real time presentation coach - and so many other ideas to inspire your use of Jev Brought to you by our wonderful sponsor 🫏 @TrustVanta Automate compliance and simplify security: vanta.com/howiai A super fun ep that could have gone for hours! Live on YT: piped.video/dAIIaepNhQM

I used my codex reset to cut this @OpenAI Dev Day recap, where I cover my favorite releases for the day (spoiler alert: I'm now an expensive Ultrafast girl) What I cover: (00:58) Dots: early impressions and rough edges (06:57) Spaces: working with humans and agents (10:37) Sites, connectors, and sharing internal tools (13:06) Models and platform: GPT-6.1 Sol (14:36) Decisions API: fast decisions with vision (17:17) Astra ultrafast: speed, pricing, and possibilities (22:25) Agents API, computer use, plugins, and plan updates (23:03) What I’d try first Full ep on YT: piped.video/watch?v=pJNM1z9l…

Live global Codex reset courtesy of @clairevo (and @thsottiaux) at DevDay

Jev week is HERE - kicking off with a 30m intro to @typesafeai Jev with yours truly. In this ep I cover: - what is Jev and what makes it different - the 3 types Jev can return - the $100k use case that cost me $0.09 - some fun product ideas to inspire you Consider this your starter Jev ep - with a follow up on Weds with the one, the only @johnlindquist on his 28 (!!!) fun Jev use cases. 👉 Full ep on YT: piped.video/watch?v=-KIBgpGA…

My mental model of AI is "dishwasher for the mind". I can offload various boring or repetitive tasks while I do other things (like volunteer at my kids school).

Excited to be co-hosting a mixer on AI, HR & the Future of Work for #SFTechWeek with @SHRM Labs! 📅 Thursday, October 8th at 4:30pm 📍 San Francisco The event will feature pitches from emerging startups at the intersection of AI, HR & the Future of Work, followed by open networking. Join us for a casual evening with free food and drinks, and opportunities to connect with founders, investors, CVC teams, and executives from @indeed and @Glassdoor, as well as the Indeed Ventures Team. 🙌 We’d love for you (and your teams) to join us! 👉 RSVP here partiful.com/e/gPHSsw6QRMO0R…

Been trying to cheer on my kids extra curricular academic work like I do their sports: live commentating on good technique, applauding the basics, clapping for good results & good efforts. Kids seem to find it weird when I compliment their technique for balancing an equation

PSA for my fellow Longhorns. Longhorn network is still a thing. Apple TV has an app.

a good time to mention we just finished the whole @once_reading program last night, covering a full year in just ~4 months! my starting 2nd grader is now reading at end-of-year level. don't tell @SebTurn but i'm vibe coding "try twice" because we need to keep going 😂