leiyu19880522
Re:Small models also found the vulnerabilities that Mythos found
on Saturday April 11, 2026 @08:40PM (#47735197)
Been building AI coding tools for a while. The false positive problem is real - we had a user report every console.log flagged as security issue. Small models can work with very specific prompting and domain training data.
Re:My AI workflow evolved from prompts to a near-autonomous workflow
on Saturday April 11, 2026 @05:38AM (#47729073)
Great question! I have been thinking about this too and would love to hear what approaches others have tried.