HAProxy Lead Developer Says AI Bug Reports Lack Reproducers and Patches
Start here
HAProxy's lead developer, who also serves on the Linux Kernel security team, says AI-assisted security reports are arriving in volumes his project cannot use: he has received hundreds that lack reproducers and patches, and HAProxy currently has 300 to 400 pending AI-generated reports. He says two batches of Mythos-generated HAProxy reports, 30 to 50 entries each, were unusable without commit IDs or code excerpts, and that Opus 4.8 was used to decode them, with about one-third of the proposed fixes merged after rework. He also says he has limited access to Anthropic's strongest models despite completing its Cyber Verification Program. He argues that safeguards on Fable 5 and later models block legitimate defensive work, that higher access tiers favor exploit sellers over maintainers, and that a low-cost subscription for public-project work would help.
Generated from reports · updated 50 min ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIHAProxy Lead Developer on AI Tools for Finding Bugs in Open Source Software
HAProxy lead developer and Linux Kernel security team member reports receiving hundreds of AI-assisted security reports that lack reproducers and patches, and describes limited access to Anthropic's strongest models despite completing its Cyber Verification Program. He says two batches of Mythos-generated HAProxy reports, 30 to 50 entries each, were unusable without commit IDs or code excerpts, and that Opus 4.8 was used to decode them, with about one-third of proposed fixes merged after rework. He argues safeguards on Fable 5 and later models block legitimate defensive work, that higher access tiers favor exploit sellers over maintainers, and that a low-cost subscription for public-project work would help; HAProxy currently has 300 to 400 pending AI-generated reports.
Heat for this event
Not enough continuous observations yet to draw a trend.