Strix retweeted
Open-weight models are getting ridiculously good.
DeepSeek V4.1-Flash-1017 just took #1 on our internal black-box pentesting benchmark: 316 known vulnerabilities across 8 live web apps.
F1 (findings combined across 3 runs) / total LLM cost:
- DeepSeek V4.1-Flash: 75.08 / $32.93
- GLM-5.3: 73.53 / $305.14
- GPT-5.6 Sol: 69.80 / $1,983.18
- Claude Opus 5: 70.12 / $3,032.39
An open-weight model outperformed every frontier model we tested, at roughly 1/90th the cost of Opus 5.
Pretty wild how quickly open models are progressing. They're no longer just the cheaper alternative. In some domains, they're already ahead.
Huge props to the @deepseek_ai team!
Full write-up, agent traces, and video: strix.ai/blog/posthog-survey…
Try Strix on your next engagement or project: github.com/usestrix/strix
We stopped at read-only checks and reported it.
Baseten confirmed it as critical and rotated the token by the next afternoon. Credit to their security team for handling it quickly.
Full write-up: strix.ai/blog/baseten-harbor…
Try Strix on your own apps: app.strix.ai/
Strix retweeted
Strix found a one-click account takeover in Granola's Electron desktop app.
A user-controlled link in the activity feed could navigate a trusted Granola window to a page we controlled, while it kept access to Granola's privileged Electron bridge.
Here's how our open-source agent found it:
Strix retweeted
I let an open-source AI hacker attack my FastAPI app.
It found real bugs, proved the exploit worked, and suggested fixes.
Passing tests doesn't mean your app is safe.






