Settings

Theme

Show HN: Beating GPT5.5-xhigh for Coding agent security with SLMs and IRM

harden.run

9 points by se4u · 6 comments · 1 min read

Reader

Coding agents craft arbitrary code so securing them is more complicated than red-teaming. We post trained a cyber-security small llm, changed how it reasons and supplemented our controls using program analysis techniques such as inline reference monitoring to outperform GPT5.5-xhigh on hard benchmarks like LinuxArena and SleightBench.

Free product available at harden.run and full benchmarks in the blog post.

4 threads
xms17189

How does the inline reference monitor handle tool calls that are dynamically composed by the coding agent, and what evidence do you expose when a call is blocked or rewritten?

pushpakpujari

Exciting. Peace of mind to run coding agents non-stop without worrying about my database getting deleted

kartikrawat

interesting. Seems like a product which should be used by everyone who is using any coding AI agent tool, and it's a free product, which makes it more of a no-brainer

mailrishav9

nice.

i've always wondered what my agents are doing behind my back, seems like a good way to see that.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection