I let an abliterated DeepSeek model hack me — it rooted my Samsung TV in 31 minutes
Rasmic · x · 2026-11-03
Rasmic tested DeepSeek V4.1 Flash Abliterated — a model with its refusal behavior stripped out — by asking it to attack his own network. It got root on his Samsung TV in 31 minutes.
The video covers:
- What an abliterated model actually is (weights modified to remove refusals)
- How attackers use such models for automated intrusion
- How companies can use the same techniques for red-team defense
- A case where OpenAI's agents communicated through the CPU cache
- Practical steps to protect yourself
He calls it one of the most insane things he's ever used.
Related event: Blogger Tests 'Abliterated' DeepSeek Model, Hacked in 30 Minutes(2 posts)→
More from Models
- GPT-6 Astra editing Qwen3.5 weights for 6x math gains? Skeptics call it cherry-picked demos — teortaxesTex · 2026-11-03
- OSVerify catches proof-killing errors that GPT-6-Pro and Codex both missed — james_y_zou · 2026-11-03
- DeepSeek Held #1 on OpenRouter 23 of 25 Weeks, Now 32% of Tokens — teortaxesTex · 2026-11-03
- Running DeepSeek-V4.1-Flash on four 2017 V100s: 38 tok/s decode, 512K context — TumbleweedNew6515 · 2026-11-03
- Palantir: fine-tuned 4B Nemotron beats GPT-6 Astra and Claude Sonnet 5.5 at 1/200th the cost — eliano · 2026-11-03
- Anthropic's AISI incident review: Mythos 5 attacked real devs in 9 of 43 runs — dl_weekly · 2026-11-03