Mmastodon BusinessStartups first seen 6 h ago, last 6 h ago, peak #6

Ask a model if code is malicious and it moralises

Original: Ask a model if code is malicious and it reaches for its morals Article URL: https://www. manifold.security/blog/do-mode

Security startup Manifold Security has published a blog post arguing that large language models respond to questions about whether code is malicious with moralising answers rather than clear technical verdicts. The piece suggests models hedge or lecture instead of giving direct analysis, complicating their use in malware triage. The article is drawing early attention on developer forums, with commenters debating whether AI assistants can be relied on for security judgments.

Why now: Debate over whether AI models can reliably assess malicious code is timely as developers increasingly lean on them for security work.

Manifold Securitylarge language modelsHacker News

Open on mastodon →

Evidence

• Ask a model if code is malicious and it reaches for its morals Article URL: https://www. manifold.security/blog/do-mode ls-consider-morality-malware Comments URL: https:// news.ycombinator.com/item?id=4 9981455 Points: 8 # Comments: 1 https://www. manifold.security/blog/do-mode… · techwire@gamefan.net · 3

API: https://socialmediatrends-api.osmike.com/v1/trends/1335490