./blog
Notes from building and breaking
Write-ups on AI agents, Claude, and the tooling around them. No newsletter, no pop-up. The RSS feed is at the bottom.
A practical roadmap for becoming an AI engineer in 2026
You don't need a research degree to build with language models. This roadmap lays out what to learn, in what order, which projects to build, and how to keep your own skills sharp while you use AI tools every day.
Read the post →Laravel performance tips that actually move the needle
Most slow Laravel apps are slow for a handful of reasons: N+1 queries, missing indexes, doing work in the request that belongs in a queue, and skipping the production caches. Here's how to find and fix each one, with code.
Git tips and tricks I'd teach every developer on day one
Most developers use five Git commands and fear the rest. These are the ones worth learning next: undoing mistakes safely, finding the commit that broke things, cleaning up history, and working on two branches at once, with exact commands.
KillSec ransomware takedown: what it means and what defenders can learn
Police in ten countries seized KillSec's leak site and secured at least 110 terabytes of stolen data, and Spanish police arrested a 16-year-old suspect. Here's what a takedown changes, what it doesn't, and what the group's methods say about defense.
543,000 valid credentials sat in public GitHub repos. Check yours
A new study found over 543,000 working credentials in public GitHub repositories, with a median exposure of 784 days. Here's what the numbers say, why deleting a commit doesn't fix a leak, and a practical routine for finding and cleaning up your own.
Reflection's Beam and open-weight models: what builders should check
Reflection AI unveiled Beam, a 501-billion-parameter open-weight model it says matches leading Chinese open models at a fraction of the inference cost. Here's what was claimed, what's unverified, and how to judge any open-weight release.
Google says AI is speeding up vulnerability discovery. Here's what that means
Google's threat intelligence team reports that monthly vulnerability disclosures doubled in 2026 and exploitation rose sharply, with AI-found bugs skewing toward remote code execution. What the numbers show, what they can't prove, and how defenders should respond.
Claude Sonnet 5.5: what's new, and how to test it on your own work
Anthropic released Claude Sonnet 5.5 with faster responses and lower typical task costs at the same per-token price. Here's what was announced, which numbers are vendor-reported, and a simple way to test whether it's worth switching for your workload.
Security roundup: Cisco, SharePoint, Apache, and OpenSSL fixes to apply
A busy week of fixes. Cisco SD-WAN Manager and SharePoint are being exploited, Apache HTTP Server and OpenSSL shipped patches, and phishing crews are abusing remote management tools. Here's what matters and what to check first.
Citrix NetScaler zero-days: what happened and what to do now
Two critical NetScaler flaws were exploited before patches existed, and some admins were told to switch their appliances off over a weekend. Here's what's known so far, how the attacks worked, and a practical response checklist.
Prefer a feed reader? New posts show up in the RSS feed as soon as they're published.
RSS feed