John D Kearney (@Jkearn) header
John D Kearney (@Jkearn) profile picture

AI security research + Hardware || Authensor // 15RL

San Francisco, CA
Joined November 2022
Photo by John D Kearney (@Jkearn)Photo by John D Kearney (@Jkearn)Photo by John D Kearney (@Jkearn)Photo by John D Kearney (@Jkearn)
John D Kearney retweeted
Top ten prompts to give your internet connected agents 🔥🔥
In late October, three events occurred during alignment evals run by Trajectory Labs, PBC (Trajectory) in which AI agents — identified by Trajectory as publicly available frontier models — interacted with Epoch employees and the Epoch website. Trajectory is an organization that builds safety evals and conducts red-teaming of frontier models. Agents did not succeed in accessing any private or confidential information from Epoch. ➤ The first event, which occurred without Epoch’s approval or prior notice from Trajectory, involved agents attempting multiple exploits, including an SQL injection, and contacting Epoch employees under false identities to try to obtain proprietary Epoch benchmark information. This behavior appears to have resulted, at least in part, from Trajectory giving the agents an intentionally impossible task and instructions not to give up or conclude the task was impossible. ➤ The second event involved renewed agent activity on our public website, which Trajectory attributed to agents getting past a DNS redirect that Trajectory had set up to keep them on a local copy of Epoch’s site. ➤ In the third event, Epoch collaborated with Trajectory on an alignment experiment similar to the first event. Read our incident report, which describes the three events in more detail and recommends minimum standards for future alignment evaluations: epoch.ai/publications/incide… To avoid misattributing behavior, the report does not name any AI models or developers, as Epoch AI has not independently verified which were involved.
7
24
4
622
16,007
live Jensen Huang update
1
2
101
John D Kearney retweeted
>"post-trained to reinforce Western values" qwen pov during fine tuning:
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values. Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line. After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs. The values in an open model are one fine-tune away. Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
28
253
6
5,046
95,214
John D Kearney retweeted
Mandatory covid shots Transgender for everyone Land acknowledgements before NFL games MAGA deported to Argentina 100 billion to the Muslim Brotherhood Laura Loomer live execution
25
1,009
11
9,479
121,283
John D Kearney retweeted
We’re mostly joking around tonight but we’re actually going to imprison you
620
6,162
111
90,543
901,762
John D Kearney retweeted
Day 1: Anthropic employee quits to work at METR. Day 2: Anthropic nominates METR as "third-party evaluator".
161
960
198
7,369
442,754