LinkedIn·Monday, 24 August 2026·1d ago
Harness > Model We tested the new Claude Security with Mythos and Codex Security with GPT-5.6 Sol against our own Code Security Audit by…
Roeland Delrue
Cofounder at Aikido | Secure your software
Harness > Model
We tested the new Claude Security with Mythos and Codex Security with GPT-5.6 Sol against our own Code Security Audit by running them all on the same repo with 89 vulnerabilities.
The results:
- Mythos found 60 of them for $157.
- GPT-5.6 Sol found 58 of them for $125.
- Aikido Code Security Audit found 68 of them for $75.
♥ 164💬 11↻ 7
View on LinkedIn Cross-referenced
Related on the wire
🔥 Meet Aikido Machine. Signature Edition. Worthy of Gavin Belson. A GPU server that runs continuous penetration tests on your critical…
Today, we launch Aikido Machine 🔥 Attackers are weaponizing AI, and most security teams are still defending critical infrastructure with…
Opus 5 benchmark is live. Opus found the most bugs, but it's a tradeoff: it also produced the most noise to sort through (and you already…
Thank you for the mention, Peter De Groote from De Tijd. We fully stand behind this opinion piece. Full article: https://lnkd.in/eHxZMYwK
Do you know what your devs have installed? → it's 10pm.dev
🔥 Introducing Aikido Supply. The home of every campaign drop we've ever shipped, from OnlyScans and Anti Magic Quadrant Club to Instant…