co-founder @raisi_ai & @UseIrisAgent | research collaborator on multi-agent simulations @ Berkeley | AI optimist
San Francisco
Joined March 2024
- Tweets816
- Following431
- Followers535
- Likes986
A team of 6 AI research agents spent 20 days building a Hearthstone bot that reached the top 100 on its server.
And the weird part is that the LLMs that built it couldn't play the game nearly as well themselves.
1/9
8/9
I think the bigger takeaway has very little to do with gaming.
An LLM doesn't necessarily need to be the best at doing a task itself.
It can build a system that's better at it, test it against reality, figure out what's wrong, and keep improving it.
That's what makes this interesting to me.
9/9
Here's the paper if you want to read it:
arxiv.org/abs/2610.33845
And the GitHub with the simulator and benchmark:
github.com/MCG-NJU/AutoTaver…
331 microsoft developers said what ai lets them do that they couldn't before. only 12% described new kinds of work. 45% described the same work, faster, and 37% work that used to be out of reach. the authors warn some could end up approving work they can no longer judge
self-reported survey at one company: about 4,000 developers were invited and 8.9% answered. the authors present approving work you can't judge as one of two possible paths, not a finding. paper: arxiv.org/abs/2610.23708
Vault is now available with the Grok bot to save passwords, credit cards, and personal details, making it easier for the agent to access things. Is 1Password going away?
@elonmusk, it would be great to add a browser extension that people can use outside the X platform for free. That would incentivize people to move away from 1Password (you would need to create an easy way to export and import data from there), and then a ton of people would move their passwords over, giving Grok bot access to basically everything (which would def increase the usage)
Dan Krieger retweeted
Linq sponsored the AI assistant meetup last night with @merit_systems, @AlphaSignalAI, @browserbase, @mem0ai & @crossmint.
Thanks everyone for coming out!
Had a great night with some incredible people.
@DavidPawlan, thank you again for hosting!
P.S. It was my first time pitching in this format, and I’m definitely keeping this video in the X archives...
Super pumped to announce 6 AI assistant legends who will be given the spotlight at the upcoming AI Assistant SF meetup on Oct 19th
- Justin Quan, Co-Founder at @tomo
- Wyatt Lansford, Co-Founder at @pally
- Dan Krieger, Founder at @UseIrisAgent
- Darshan Golchha, Growth at @orchid_hq @onkeiki
- Carlo Edoardo Ferraris, Founder at @NaturaAI
- Stanley Virgint, Founder at @soarapp
maybe even a pitch prize to be announced...
If you run an AI assistant, hit me up!
RSVP Here: luma.com/wabd65c0
