most people don't understand how much leverage a swarm of personal agents gives you. i have poke, instinct, muse, dot, grok bot, pickle, bunch of other agents you've never even heard of doing my bidding (all texting me at once when an unimportant email hits my inbox)
@packym
-
Using AI to turn an essay into a short movie concept
By
–
I wanted to make a short movie based on the Airbound deep dive. Fed dot my essay, told it I wanted to make a short movie that’s a package’s journey before and after Airbound as a mix of a Steve Cutts video into Pixar movie. With a little back and forth on story, emotional
-
Short film KILO made with Runway ML
By
–
KILO
— Packy McCormick (@packyM) 3 octobre 2026
A short film based on the @Airbound_Aero Deep Dive.
Made with @runwayml. https://t.co/yxoMA7cnRs pic.twitter.com/9g9eZ52BYAKILO A short film based on the @Airbound_Aero Deep Dive. Made with @runwayml
. -
AI agent dot controls Claude desktop app
By
–
Just asked dot if it could control the Claude app on desktop and it can
-
Humanity’s immune response to mediocre AI content
By
–
It's heartening to see humanity's immune response to mediocre AI-generated content here. You can do it, you can take the easy way out, but you will be mocked and lose the respect of your peers.
-
Critique of the Real Intelligence of Claude and ChatGPT
By
–
I have no sophisticated benchmarks other than: I don't know how you can see Claude or ChatGPT conceive in the same way and write in the same way and believe that it is intelligent in any real way.
If there were 'intelligence' in there, this… -
Founders test models on unsolved problems: completing work vs making work
By
–
Very good point. See something similar talking to founders with very specific hard problems to solve – they test each new model for the ability to churn through their list of unsolved problems. In both cases, completing work v making work.
-
User switches to Opus 4.6 as daily driver for cybercrime
By
–
I've made the switch back to Opus 4.6 and it's way better. For doing cybercrime, I will continue to use the most advanced models, but 4.6 is my new daily driver.
-
GPT 5.5 Erdos breakthrough in AI research
By
–
Retatrutide stuns in Phase 3 trials.
Colossal hatches chick from artificial egg.
SpaceX Launches its S-1.
GPT 5.5 makes Erdos planar distance breakthrough.
SendCutSend raises $110M at $1B. + Science Breakthroughs, Anthropic, Quantum, Grindslop What a week for the optimists.
