Is GLM-5.2 really closing the gap to Anthropic - and at just a fraction of the cost - or is it just more AI hype? I think so, and let me show you why.
Why my Scrapy project plays a triumphant fanfare when a crawl finishes clean and a sad trombone when it doesn't, and how I finally learned how to build Scrapy extensions (it's easy)
"Four people, four diets, two work schedules, and a baby who answers to nobody. That's what finally made me build a personal agent." A walkthrough of the actual architecture I run to hold my household and my DevRel work together — profiles, skills, memory, and the web-data layer that makes it all reach the live web.
For 20 years, we were told “data is the new oil”. That’s no longer true. In the era of the fluid web, information is more fundamental, cleaner and abundant than that.
AI agents need access to public web data, right now. Tools connected to web scraping APIs empower agents to return live data quickly.
A viral clip from Claude Code's creator put a name to something a lot of us have been circling: loop engineering. Here's why web scraping may be its best-fit domain — and what that means in practice.
No-one likes an out-of-touch AI assistant. Fortunately, rapid refreshing can keep AI models aware of the very latest public information.
AI agents can generate code, suggest selectors, and draft crawl logic. What they can't do is design the system that decides when to stop, what to trust, and how to recover when the web pushes back. That job still belongs to a human.
_HFpro5d6k3.png&w=256&q=75)
_E4PyVpfAxa.png&w=256&q=75)
-(1).png&w=1920&q=75)
-(1)_VZGHqxCgXV.png&w=1920&q=75)
