
jasonpurdy
808 posts

jasonpurdy
@jasonpurdy
Founder, Neuron | Previously Apple, Square, Dialpad


March was packed at SPC... a new model from @LumaLabsAI, a robot debut from @NobleMachines, new tools from @world_lica, @spc_india's 2nd-ever Demo Faire, events with @eladgil, @drfeifei, @stephen_wolfram, @Thom_Wolf, & more. Read on⬇️

Claude Code has a regex that detects "wtf", "ffs", "piece of shit", "fuck you", "this sucks" etc. It doesn't change behavior...it just silently logs is_negative: true to analytics. Anthropic is tracking how often you rage at your AI Do with this information what you will


I’ve always been someone who dabbled in it multiple aspects of life at the same time, juggling several hobbies and side projects. Twelve years ago I started TheBayRide.com, a 135 mile charity ride around the whole Bay Area. Compounding works and we’ve grown to over 1000 riders this year. My primary focus for 2026 is growing Neuron, so I needed to automate as much of TheBayRide as possible (shout out to BikeMonkey for taking SO MUCH off my plate). Earlier this year I built an entire automated marketing agency inside TheBayRide that emails me once a day to approve social media posts, synopsis of comments and replies it handled, updates on ad performance, with a particular focus on confidence measurements along with proposals to improve. Each email has a link I can click to a dashboard to then take an action. Now that Neuron is live in the App Store (apps.apple.com/us/app/neuron-…) I realized I can reuse A LOT of this to grow Neuron too. In fact, more importantly I realized “why am I emailing myself when I have my own messaging protocol?” Duh. I can now send myself a neuron message instead of an email, click either “Approve”, “Edit”, or “Skip” buttons. If I choose edit I can simply reply with edits to be made in natural language and Neuron makes the edits and sends me another approval message in Neuron. Change a photo, edit the copy, etc. and within seconds I have an updated social media post or ad ready to be posted, monitored and replied to as needed. We’re just getting started, but when you see a Neuron’s ad you’ll know how it was made.








Claire Vo's first day with @OpenClaw it deleted her family calendar. Now she runs 9 agents across 3 Mac Minis, and said "I haven't felt like this since I was a teenager learning to code." Her sales agent Sam does a daily CRM sweep, identifies decision-makers from new signups, and sends personalized outreach—replacing a part-time salesperson she was paying 10 hours a week. Her home agent Finn pings her and her husband every day at 3pm: "Which of you is picking up which kids?" Then flags when the oldest's basketball conflicts with the middle kid's soccer and asks how they want to split duties. She also has agents for podcast prep, kids' homework help, and course project management. Claire (host of How I AI, founder of @ChatPRD) started as one of OpenClaw's most vocal skeptics. She now calls it "a ChatGPT moment." In our in-depth conversation, she breaks down: 🔸 Her exact setup: Mac Mini, separate Gmail, dedicated local account 🔸 The progressive trust model: first calendar access, then read email, then draft, then send — just like onboarding an EA 🔸 Why one agent is a mistake—and why she thinks about it like Slack channels, not a single assistant 🔸 How to use Claude Code as a "brain surgeon" to fix and manage your OpenClaw when things break 🔸 "The yappers API" — why rambling into a voice note is the highest-bandwidth way to set up your agent 🔸 Why management skills matter more than technical skills for making this actually work Listen now 👇 youtu.be/DIa0MYJzM5I






Introducing Chroma Context-1, a 20B parameter search agent. > pushes the pareto frontier of agentic search > order of magnitude faster > order of magnitude cheaper > Apache 2.0, open-source






