Auto Added by WPeMatico
The following article originally appeared on Addy Osmani’s blog and is being reposted here with the author’s permission. A long-running AI agent can keep making progress over hours, days, or weeks. It can do this across many context windows and sandboxes, recover from failure, leave structured artifacts behind, and resume where it left off. For […]
The following article originally appeared on Paolo Perrone’s The AI Engineer Substack and is being reposted here with the author’s permission. Your team picks LangGraph for a customer support chatbot. Three weeks in, you’ve got 14 nodes in a state graph, a custom checkpointer writing to Redis, and retry logic for tool calls that fail
I set up an AI agent on a rented GPU, pointed it at a training script, and went to bed. By morning it had run 40 experiments, improved validation loss by 5.9%, and cut memory usage from 44 GB to 17 GB. It also spent four hours chasing a bug that a linter introduced behind
I Let an AI Agent Run 40 Experiments While I Slept Read More »
DJ Patil has spent the past several months on a listening tour. Wherever he travels, he finds a local university, pings faculty and students and anyone else who wants to show up, and runs an AMA. He’s heard from grad students who can’t get callbacks, hospital administrators absorbing federal policy changes that land like a
A third of the way into a security-operations guide that Anthropic published in April 2026, wedged between a recommendation to patch CISA’s Known Exploited Vulnerabilities list and a suggestion to automate your deployment pipeline is a small recommendation: “Use EPSS to prioritize the rest.” For anyone who has worked on a vulnerability backlog in the
As syntax becomes cheap and abundant, architectural control becomes the scarce resource. Effective governance starts upstream, where intent, constraints, and threat models shape the agent’s working context before generation begins. The goal isn’t better prompting but build-time boundaries that prevent structurally invalid code from entering the system. The Frankenstein factories The dark factories (as Dan
Adam Tooze recently shared a piece from The Economist about Brazil’s push for what it calls “medical sovereignty,” the determination to make its own vaccines and the active ingredients that go into its medicines rather than depend on supply chains it doesn’t control. Brazil already produces a large share of its own medicines through public
AI Sovereignty and the Architecture of Participation Read More »
With the rise of agents, many people have been proclaiming that the age of software as a service (SaaS) is over. Who needs to subscribe to a service when you can create your own software with a few English-language prompts and a few dollars spent on tokens? Your own software, most likely a skill that
The following article originally appeared on the Asimov’s Addendum Substack and is being reposted here with the author’s permission. Bill Gurley has an excellent article on what he calls open source strategy, which we recommend reading. There is a lot to debate about his concluding argument in particular: that open-weight models are central to keeping the AI market
This is the seventh article in a series on agentic engineering and AI-driven development. Read part one here, part two here, part three here, part four here, part five here, and part six here. This is the latest article in my Radar series on AI-driven development and agentic engineering, and I have to admit that this one took a bit of
Your AI Agent Already Forgot Half of What You Told It Read More »
