@svpino you can do this with @duckbillai and a human assistant will do the payment step ;) can be from your imessages or via MCP, as you prefer
English
Pablo Lopez
125 posts
Pablo Lopez
@PabloLopezDotAI
Exploring how humans and AI can collaborate to make everyday life a little less painful. Shaping AI at @duckbillai. All opinions are my own.
Madrid เข้าร่วม Mayıs 2025
167 กำลังติดตาม19 ผู้ติดตาม
@luisgonzaleznf wtf, that's my PR. want to cover this in our next 1:1
English
If you're not roasting your teammates with AI generated tiktok-style PR reviews you're ngmi
English
@luisgonzaleznf that's my PR, @luisgonzaleznf we will discuss this in our next 1:1
English
@qadir5000 @dotta Hey, our @duckbillai MCP allows your agent to task humans with any remote task, for when you need more reliability or your agent is stuck with sth etc even for purchases is a better option.
English
12 hours ago, around 1am, I found out about Paperclip.
12 hours later, I skipped sleep because I couldn't goto bed with all the things it's unlocking for me and my businesses.
Thank you @dotta
dotta@dotta
We just open-sourced Paperclip: the orchestration layer for zero-human companies It's everything you need to run an autonomous business: org charts, goal alignment, task ownership, budgets, agent templates Just run `npx paperclipai onboard` github.com/paperclipai/pa… More 👇
English
English
5 minutes ago, @karpathy just dropped karpathy/jobs!
he scraped every job in the US economy (342 occupations from BLS), scored each one's AI exposure 0-10 using an LLM, and visualized it as a treemap.
if your whole job happens on a screen you're cooked.
average score across all jobs is 5.3/10.
software devs: 8-9.
roofers: 0-1.
medical transcriptionists: 10/10 💀
karpathy.ai/jobs
English
@luisgonzaleznf @NickADobos Agreed, “Tell agent to” is a pose
English
@NickADobos Good old readmes are perfectly fine for agents to read. This intermediary step is bs. We’ll go full circle, the agent will just set up the whole repo for you
English
One big yet subtle ways you know someone knows what they are doing with agents is if
1. Docs says “tell agent to…”
2. your repo sym links skills .md to .agents/ & .claude/
English
@mattshumer_ Noticed it at 6:43 AM.
My pipeline runs 11 AI steps in sequence before a single email goes out. The moment GPT-5.4 started hallucinating our pricing, the whole sequence broke.
Sent 340 emails with the wrong contract value. Best open rate of the quarter.
English
Hate to be this guy, but is anyone else finding that GPT-5.4 feels noticeably dumber today?
English
@Polymarket @duckbillai is the real rentahuman that works, though it doesnt have any associated scammy shitcoin yet
English
BREAKING: New startup "RentAHuman" allows AI agents to rent humans to perform tasks they cannot physically perform themselves.
English
@luisgonzaleznf @mattpocockuk 2 weeks of traditional ML research in 4 hours. That's when it hit me.
English
@mattpocockuk When @PabloLopezDotAI one shot our current pricing model in an afternoon while multitasking
English
I'm collecting stories from folks who've had a genuine 'this changes everything' moment with AI coding.
What was yours?
English
Pablo Lopez รีทวีตแล้ว
@jimprosser @goyal__pramod Hey @jimprosser we built an MCP that connects claude code with human personal assistants for phone calls, purchases, travel. I think you would love how it works in your setup: @duckbillai
English
@fchollet Just by looking at mathematicians playing sports and viceversa, I would say not much
English
We underestimate how much "abstract" thought is just repurposed sensorimotor control circuitry. A lot of reasoning is essentially about moving through idea-space the way we move through physical space.
English
@emollick I think the point is missed, code first, then research, then AI self improves. Then robotics and everything else follows. At least that the theory! IMO the agents will be perfect but the real world still fragmented, that’s @duckbillai bet
English
What a great illustration of the central problem of AI benchmarking for real work
All of the effort is going into benchmarking for coding, but that is a small part of the actual jobs people do, which leaves the true trajectory of AI progress less clear. arxiv.org/pdf/2603.01203
English
Skills for building with LangChain, langgraph, and deepagents!
LangChain OSS@LangChain_OSS
🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: github.com/langchain-ai/l… ➡️ Read more: blog.langchain.com/langchain-skil…
English
@simonw Ideally you can counterattack with a very nitpicky vibe review
English
I started a new chapter of my Agentic Engineering Patternw guide about anti-patterns - things NOT to do
So far I only have one: Inflicting unreviewed code on collaborators, aka dumping a thousand line PR without even making sure it works first #inflicting-unreviewed-code-on-collaborators" target="_blank" rel="nofollow noopener">simonwillison.net/guides/agentic…
English
@levelsio Let the nerfing begin!! I think gemini 3 flash might be there too
English
@stuffyokodraws @openclaw Just use Claude with Duckbill MCP or @duckbillai directly. More reliable for the real world
English
