Member of Technical Staff @openclaw 🦞 Prev Founding Engineer @continuedev (acquired by Cursor)
San Francisco
Joined February 2020
- Tweets1.2K
- Following722
- Followers1.5K
- Likes3.7K
Patrick Erichsen retweeted
Four OpenClaw developers made @linuxfoundation’s Top 100 contributors list:
#1 @steipete
#7 @vincent_koc
#33 @obviyus
#57 @dallinfinite
569,649 contributions in a year. 13.8% of the Top 100 total.
Thank you, open-source community.
insights.linuxfoundation.org…
One of the blurriest boundaries with AI is when assistance turns into automation, and when that is desirable
I’m fine to have an agent automate much of my software engineering work.
But do I want an agent to automate my friendships? No - but where is that line crossed?
Is using a calendar to remember a friend’s birthday “automation”? What about helping draft the first pass of a birthday card?
We all want AI to automate the drudgery in our lives but it’s easy to slip into automating the parts that should remain human
anoma.ly/notes/opencode-relo… from @opencode team may have the most enjoyable easter eggs of any blog ive read, kudos!
Personal agents are the best embodiment of the promises of AI - to empower more people, from more diverse backgrounds, to do more creative and ambitious things in their lives.
> Whether this all collapses into one giant brain, sure, it’s possible, and the reasons may have more to do with economics and politics
even this seems unlikely as local models cross the threshold for a wide range of basic tasks
i dont need AGI to run my home automation agent
.@bratton argues Yudkowsky misunderstands evolution, and explains why AI may never converge into one giant superintelligence:
"Without being too spicy, I don't think Yudkowsky really understands evolution as well as he thinks he does."
"It’s a very low-resolution understanding of evolutionary dynamics applied to what will inevitably be a much more complex problem."
"There will be giant models, in the same way you might imagine scales of species in a rainforest. They’re not all operating at the same spatial and temporal scale."
"Whether this all collapses into one giant brain, sure, it’s possible, and the reasons may have more to do with economics and politics."
"But biology has never arrived at a solution where it’s going to make one giant instantiation of a particular form of mind and consolidate everything together."
Patrick Erichsen retweeted
.@bratton argues Yudkowsky misunderstands evolution, and explains why AI may never converge into one giant superintelligence:
"Without being too spicy, I don't think Yudkowsky really understands evolution as well as he thinks he does."
"It’s a very low-resolution understanding of evolutionary dynamics applied to what will inevitably be a much more complex problem."
"There will be giant models, in the same way you might imagine scales of species in a rainforest. They’re not all operating at the same spatial and temporal scale."
"Whether this all collapses into one giant brain, sure, it’s possible, and the reasons may have more to do with economics and politics."
"But biology has never arrived at a solution where it’s going to make one giant instantiation of a particular form of mind and consolidate everything together."
Patrick Erichsen retweeted
NVIDIA RTX Spark and the Case for Owning Your AI
@NVIDIAAI’s Apoorv Chaudhary joins @hrudolph and @Pat_Erichsen to discuss local AI, privacy, hardware limits and where cloud models still fit.
Watch or listen to Episode 14 of The ClawCast:
openclaw.ai/podcast/episode-…
Chatting local AI at OpenClaw and Friends with @NVIDIAAI and @Microsoft !
my @openclaw can now program my @FellowProducts coffee machine via iMsg ☕️
openclaw skills install @patrick-erichsen-2/fellow-aiden
more and more i find myself reaching for words like "seam" or "load bearing" even though i know its slopspeak
i think this happens because to communicate well with an agent you have to use their own jargon
eg if agent says "i added a load bearing seam", even if i dont want to use slopspeak, its most efficient for me to just go along with it and say "remove that seam"
slowly over time this gets reinforced until by muscle memory i reach for terms like "seams" against my own will
quite insidious!
Patrick Erichsen retweeted
I love hearing from people like @ArkStabler who are using OpenClaw to help businesses grow
But I REALLY love hearing that he helps people like Donna become OpenClaw power users
the best open source software for agents is the one that is the most remixable
@openclaw achieves this through our plugin ecosystem - we aim to make the harness maximally pluggable.
think you have a better idea for how memory should work? build a plugin!
dont like how we assemble context? build a plugin!
Patrick Erichsen retweeted
Tomorrow I'm hosting a space to talk about the landscape of the agent wars
There is too much to keep track of so join this space each week to get caught up!
nitter.cf/i/spaces/1PJqrNBlReMxb
don't underestimate how good agents are at using Playwright to generate before/after proof videos!
captions, zoom, etc
one of the highest fidelity ways to verify something works correctly
skill we use at @openclaw for this: github.com/openclaw/openclaw…
Patrick Erichsen retweeted
Wow,
Thanks to the crew and to @openclaw for this.
Y’all are doing incredible work and it was amazing to have this chat!
@heyneighbor
@hrudolph
@patrickerichsen
Live Q&A with Patrick and Hannes | The ClawCast Episode 13 nitter.cf/i/broadcasts/1AJEmvrja…
