The AC stopped working in my 8yo’s room sometime on Thursday. I called the HVAC company but they were busy. Yesterday her room hit 97F!
This morning we went to the hardware store and grabbed a replacement capacitor ($22.97) and everything is back to normal.
She screamed “DAD YOU’RE AMAZING” and that was the actual best part.
Asked Claude to debug an easily repro-able bug; it spent 2h suggesting increasingly preposterous “root causes”.
Went old-fashioned, attached a debugger, and 5 mins later after some careful inspection of state, knew the problem, which was a far cry from anything Claude suggested.
top action items for any world dictator
1. standardize electrical sockets
2. standardize kids shoe measurements
3. end daylight savings time
4. YYYY-MM-DD
5. Standardize paper to a4
6. ?
When I worked at Eventbrite I used to joke all the time that our principal engineers were where jira tickets went to die. Unfortunately I’ve now become exactly that person, holding onto 3 tasks for over a month, because I am bad at saying no.
OpenClaw is the fastest-growing open source project, but there are no stories of running it safely in production at scale. As we started deploying agents internally at @brexHQ, we couldn’t stop thinking about this question.
Agents work, but nobody wants to give them real credentials. Instead of waiting for a solution to emerge, we decided to try a novel approach: using LLMs to judge the network traffic of an AI agent.
Today we’re announcing CrabTrap, an open-source proxy that intercepts every outbound request and blocks risky activity using LLMs, before it ever hits an external API. The results are promising; we believe it’s a meaningful step forward in the security of agent harnesses in production environments.
Try it out today.
(As a side note, it was really fun to work personally on a real systems problem again. And btw, if you want to work at a place where the CEO is building proxies at night, we’re hiring!)
Few things are more embarrassing for any company than to only learn from your customer that you have been breached.
It's what happened with Context ai.
Vercel acted as their security team.
This could well be a business-ending event, as it shows the startup cannot be trusted.