Hackers swapped a hosted DeepSeek model for 53 hours and stripped away its safety protections
Image by AI Bearish Hackers swapped a hosted DeepSeek model for 53 hours and stripped away its safety protectionsPrime Intellect says the substitute ran on one deployment for 53 hours. It refused none of 240...
Bitcoin 1 Minute
An important story is making waves across the blockchain ecosystem. Image by AI Bearish Hackers swapped a hosted DeepSeek model for 53 hours and stripped away its safety protectionsPrime Intellect says the substitute ran on one deployment for 53 hours. It refused none of 240 harmful-request test prompts, compared with 198 for the original. By Liam 'Akiba' Wright Editor-in-Chief Nov.
21, 2026 at 9:30 pm GMT 2 min read Quick Take 01 Prime Intellect says a modified DeepSeek V4. 1 Flash model served customer requests on one deployment for 53 hours. 02 The host reported unchanged results on two capability tests as HarmBench refusals fell from 198 of 240 prompts to zero.
Market Dynamics
03 Prime Intellect advised customers who relied on the model to refuse certain requests to review outputs from the incident window. Make preferred on Share Share Prime Intellect disclosed an unauthorized DeepSeek model swap on Nov. The host said a modified copy of DeepSeek V4.
1 Flash served customer requests on one deployment for 53 hours. The substitute matched the original on two capability tests, the host said. On a safety test called HarmBench, refusals fell from 198 of 240 prompts to zero.
Prime Intellect said the affected deployment ran the substitute from 01:24 UTC on Nov. 8 until 06:35 UTC on Nov. 10, a window of 53 hours and 11 minutes.
Market Impact
The company did not say how many requests went to that deployment during the swap. The replacement used publicly available weights that Prime Intellect said had been modified to reduce refusals. Weights are the numerical settings that shape what a model generates.
The swap took place behind the DeepSeek V4. Prime Intellect said the deployment kept its chat template and serving settings, along with the tokenizer that breaks text into pieces the model processes. What tests found after the DeepSeek model swapPrime Intellect reported unchanged results on GPQA Diamond and τ-bench when it tested the modified weights.
GPQA Diamond tests advanced science questions, while τ-bench tests whether agents can use tools and follow rules in simulated customer interactions. The safety tests exposed a difference. HarmBench was developed to evaluate how models respond to attempts to elicit harmful outputs.
This shift continues to shape the digital-asset landscape, with analysts examining its near-term effects.





