
Can Opus 4.8 Be Used to Edit Technical Articles?
A technical editor puts Anthropic's Opus 4.8 to work as an agentic editor on a code-heavy article to determine how effective (or necessary) it is.

A technical editor puts Anthropic's Opus 4.8 to work as an agentic editor on a code-heavy article to determine how effective (or necessary) it is.

A new IETF draft from authors at OpenAI, Okta, AWS, Ping, and Zscaler argues AI agents should be treated as workloads with short-lived cryptographic identities — not handed your long-lived API keys.

A roundup of the European "sovereign" productivity suites trying to replace Google Workspace and Microsoft 365 — who builds them, what's inside, and whether you can actually use them yet.

We read all 416 comments in the 906-point Ask HN thread on local coding models and counted who actually runs what. Qwen dominates, most say it's still not a frontier replacement, and every number here is backed by the comments.
![Is it feasible to self host an open source EU Sovereign productivity suite in 2026? [A Mijn Bureau Review]](/img/articles/mijn-bureau-review/cover.jpg)
I spent a few hours self-hosting Mijn Bureau, the Dutch government's open-source productivity suite, as an alternative to Google Workspace — here's what worked and what didn't.

A sourced roundup of what real people and companies spend on AI tokens, from $0 (firms that banned AI coding) up to $1.3M/month for a single OpenAI employee, sorted low to high in USD per person per month.

We built Otto, a meeting assistant that listens to any call and answers out loud when addressed by name. Here's how we used Deepgram's Nova-3 transcription and Aura voices to make it work in real time.

A GitHub issue called "Please Do Not Vibe Fuck Up This Software" hit the top of Hacker News this weekend. Here's what's actually going on with rsync, and a reminder of how to be a good open source citizen.

Stack Overflow's traffic decline gets blamed on AI. But every online community needs critical mass to survive, and once that mass cracks they tend to die fast. Here are nine others that went the same way.

A four-stage agent experience audit of GitGuardian: testing discoverability, onboarding, integration, and agent tooling, with a competitor comparison.