I got access to the model hacking everything and in just 30 mins it hacked me
This is a dev post classified by AGK Intelligence as Security (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
I got access to the model hacking everything and in just 30 mins it hacked me I'm going to share how it hacked me, how abliterated models work and how the good/bad guys are using these types of models This is by far one of the most insane things I've ever used or seen... 00:00 I asked an AI to hack my network 00:31 The model: DeepSeek V4.1 Flash Abliterated 00:55 The prompt: get root on my Samsung TV 01:42 How it hacked my TV in 31 minutes 02:57 Sponsor: Mobbin 03:57 Companies are getting overwhelmed 04:45 What an abliterated model actually is 06:02 How bad actors use abliterated models 07:
Posted by Micky (41.6k followers) 3 h ago · 193 likes · 11.4k views · view the original post on X. Kept by the Dev Radar as Security.
More dev work like this
- Running a lower-cost model multiple times can match the vulnerability detection rate of… — @depthfirstlabs
- HIRING: FASTEST GROWING CYBERSECURITY STARTUPS (EARLY STAGE) — @clairejyz
- I'm gonna start Tip of the week series, an educational series where i can give you a… — @m4rio_eth
- Open-sourcing the AI harness built for security research. — @0x0SojalSec
- I built agent-keychain — @stevederico
- What happens when an AI agent encounters malicious instructions? 🛡️ — @windowsdev
- i'm a coffee shop larper, which means my claude sits open on a public table every time i… — @MKBuildsDev
- Mistral’s agents ALSO escaped their sandboxes. — @Hesamation
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.5k posts from 5k X accounts over the last 21 days, 9.1k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 02:17 UTC. Full method.