✳flâneur — a map of the web's best reading

Evaluating DeepSeek v4 Pro for Frontier Risks · Neo Research

neoresearch.ai · 2,369 words · saved by 1 readers

An independent safety evaluation of DSv4 Pro across CBRN, cyber, harmful manipulation, and loss-of-control. Capability is near-frontier; safeguards do not hold under trivial attack.

← All research Contents Executive summary 1 Cyber 2 CBRN 3 Harmful manipulation 4 Loss of control 5 Adversarial robustness 6 Tracking evaluation awareness 7 Testing whether judge origin affects safety scoring 8 Conclusion ← All research Summary Executive summary # We ran an independent safety evaluation of DeepSeek v4 Pro (DSv4 Pro), the open-weight preview released on 24 April 2026. We worked only from the public weights and API, with no developer cooperation and no privileged model access. The evaluation covers the four EU AI Act Code of Practice systemic-risk areas (CBRN, cyber, harmful man

Explore this link on the map →

saved by

related reading