2 points, 0 comments on Hacker News
Source: [Hacker News](https://github.com/avelone123123/shard)
A dev. to post this week ran a clean experiment: give an AI coding agent permission rules ("ask before git push / gh pr create"), then watch whether they fire. First run: the agent pushed and opened a PR without asking once.
Claude Code on my laptop could read my folder of PDFs. Codex on my desktop needed one answer from those PDFs and couldn’t reach them. So I copied the question from one terminal, pasted it into the other, waited, and copied the answer back.
When engineering teams start their first SOC 2 audit to unblock an enterprise deal, most underestimate the real Year-1 budget because they only price out the CPA audit fee. In reality, a SOC 2 budget breaks down into four distinct cost centers: Independent CPA Audit Fee: ~$11,000–$18,000+ for st...
I run a small studio site that hosts 37 AI image models side by side, and I test each one the same way: real prompts, first output kept, no re-rolls. Ideogram 4. 6 launched November 19 with three headline claims — the best text rendering in the business, native 4K output, and precise multi-step ...
When an Industrial Gateway Ships With an Open Flow Editor Siemens has disclosed CVE-2026-58115, a missing-authentication flaw in the Node-RED HTTP interface on SIMATIC IoT2050 devices running Industrial OS with Node-RED installed. The score is 10. 0 under both CVSS 3.
Multi-session agent work has a predictable failure point: the context boundary. Session A does three hours of work, hits its limit, and dies. Session B starts fresh — no memory of why the auth refactor touched the billing module, no record of which approach was tried and rejected, no list of wh...