Steve Gibson
speaker
17,616 appearances
14 recordings
1 series
first heard May 2026
last heard 2 Sep
Steve Gibson’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 14 in all, peaking in Jul 2026 with 5.
Appearances
behavior.
So it turns out it could be removed.
So
Okay.
So f for what it's worth, when we encounter the term obliteration.
This is what is meant, you know, not obliteration, abliteration.
So just to put a final point on it, a a hugging face blog posting in the summer of 2024 that is, you know, following this research was titled Uncensor Any LLM with Obliteration.
And I'm going to share just the intro from that posting to give everyone a sense for what that that earlier where for where that earlier research led, which is here.
The blog says the third generation of Lama models provided fine tunes, then it says in parens, instruct versions that excel in understanding and following and
instructions.
However, these models are heavily censored, designed to refuse requests seen as harmful, with responses such as, as an AI assistant, I cannot help you.
While this safety feature is crucial for preventing misuse, it limits the model's flexibility and responsiveness.
In this article, we will explore a technique called obliteration.
that can uncensor any LLM without retraining.
This technique effectively removes the model's built-in refusal mechanism, allowing it to respond to all types of prompts.
The code is available on Google Colab and in the LLM course on GitHub.
So then it says, what is obliteration?
Modern LLMs are fine-tuned for safety and instruction following, meaning they are trained to refuse harmful requests.
In their blog post, R Didi et al, and that that is the that is the previous root research that I was referring to, the research in the summer of 2024, R Didi et al.
have shown that this research.
Showing 2101–2120 of 17,616 · page 106 of 881
← Previous
Next →