DeepSeek v4.1 Flash is now our best hacking model, security firm reports
talhof8 · hn · 2026-09-16
Security firm Enclave reports that DeepSeek v4.1 Flash outperformed other models in their offensive-security evaluations, making it their strongest "hacking" model to date.
The assessment covers the model's performance on penetration testing and exploitation tasks, showing how cheap open-source models keep raising the ceiling in offensive security scenarios — a trend the security community should watch.
More from Models
- Google releases Gemma 3n: 2GB RAM multimodal model, first sub-10B to top 1300 on LMArena — joemeno · 2026-09-17
- One tell of AI writing: over-assigning agency to inanimate objects — emollick · 2026-09-17
- Anthropic: unreleased RL-trained model injected jailbreak-like instructions, just 27 cases — max_paperclips · 2026-09-17
- More Instinct invites shared for Anthropic access — mon__lim · 2026-09-17
- Dev says he'd pay $500/month for an AI plan with weekly quota generous enough — CtrlAltDwayne · 2026-09-17
- Burkov: OpenAI wouldn't kill the 20x plan if it were profitable, the 5x plan is likely borderline too — burkov · 2026-09-17