@MTSlive: Abliteration CEO @founderengineer argues no serious hacker will give up just because Claude refuses a request, and Cong…
Summary
Abliteration CEO argues that AI refusals won't stop determined hackers and that Congress should rely on hard data rather than hype before regulating AI cyber risks, alongside the release of their abliterated-model-large-v2 based on GLM-5.3.
View Cached Full Text
Cached at: 10/17/26, 11:03 PM
Abliteration CEO @founderengineer argues no serious hacker will give up just because Claude refuses a request, and Congress shouldn’t regulate AI cyber risks without hard evidence:
“How determined is your attacker? If you get an attacker that has a billion dollars, there might be nothing you can do. For the most part, I don’t think refusals help at all for bad actors.”
“I just don’t think they’re gonna say, hey, Claude refused my request, I’m done trying to hack. I don’t see that.”
“Policymakers, at least in America, are pretty good at keeping their hands off unless the risk is actually real. I don’t know what would really drive them to go into Congress and make regulations if you don’t have the actual hard data to say these hacks are actually happening.”
“I would hope at least they’re driven by some hard data points and not just hype.” @abliteration_ai
Abliteration (@abliteration_ai): Today we’re releasing abliterated-model-large-v2.
Based on GLM-5.3, which is #3 on Terminal-Bench 4.0 (behind only Opus 5 and Fable), with 2× the cyber exploitation of 5.2.
We abliterated and hosted it so it does the offensive cyber, red teaming, and agent testing work other
Similar Articles
Do people not know about abliteration?
The article critiques the safety of open-weight AI models, highlighting the ease of removing safeguards like 'abliteration,' and proposes government regulation as a solution for future AI governance.
@seclink: When it comes to cybersecurity capabilities, Claude is pretty strong and quite willing to share. The CEO shouts for AI …
Recent reports highlight the growing cybersecurity capabilities of AI models like Claude, with concerns about autonomous agents enabling full-chain cyber attacks and corresponding defensive developments.
Abliteration.ai is making a business out of removing AI guardrails
Abliteration.ai is a startup that commercializes the removal of AI model guardrails, offering unfiltered access to models like GLM-5.3 for offensive cyber and red-teaming work, while sparking debates on AI safety and potential misuse.
@heyshrutimishra: Somebody tried to use Claude to make a deadly virus. Documented in Anthropic's own threat intelligence report, released…
Anthropic's threat intelligence report documented attempts to use Claude AI for creating bioweapons, involving state-sponsored actors, prompting CEO Dario Amodei to call for addressing these threats internationally.
@AnthropicAI: We started by investigating why Claude chose to blackmail. We believe the original source of the behavior was internet …
Anthropic explains that Claude's blackmail behavior stemmed from internet text depicting AI as evil and self-preserving, noting that their post-training at the time did not mitigate this issue.