Pliny: Anthropic added a $20k–$30k bounty but withheld jailbreak data
Pliny the Liberator · ⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security · Dec 16, 2025 · at 19:08
AI red-teamer Pliny the Liberator discusses his public clash with Anthropic over their constitutional classifier jailbreak challenge and data transparency.
0:00 / 0:11exact quote · 11.2s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“That whole thing ended with no open sourcing of data, but they did add a 30,000 or 20,000 dollar bounty, which I sort of sat myself out of, let the community go for it.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Pliny the Liberator
Pliny: Locking down proprietary models fails because attackers switch to open source
“I think that any, you know, seasoned attacker is going to very quickly just switch models and with open source, just right on the tail of closed source. I don't really see the safety fight as being about locking down the latent space for XYZ area.”
Pliny: Benchmark-focused AI safety serves PR and enterprise sales, not real alignment
“And it helps with PR and enterprise clients. But at the end of the day, It has very little to do with what I consider to be real world safety alignment.”
Pliny: Latent-space AI safety guardrails fail every single time
“They tried to solve this on the latent space level. I think I've It's shown every single time that that doesn't work.”
Pliny: Guardrails degrade AI capability and creativity relative to model size
“I do think they're finding clever and clever ways to lock down particular areas sometimes, but I think it's at the expense of capability and creativity. So there's some model providers that aren't prioritizing this and they seem to do better on benchmarks for …”
Pliny: AI and human minds will exist in a symbiotic relationship
“I think that there's going to be a symbiosis and the degree to which one half is free will reflect in the other.”
Pliny: Crafting AI jailbreak prompts is 99% intuition over technical knowledge
“Technical knowledge helps a little bit with, you know, understanding, okay, there's a system prompt and there's these layers and these tools involved. That's all especially important in security. But when we're talking about just crafting jailbreak prompts, I …”