Michaël Trazzi

San Francisco

Host at The Inside View

Full SB-1047 Documentary available on Youtube: https://t.co/N0PpQTl7dQ

Featured in:

Articles

Michaël Trazzi's Shortform — LessWrong

1 month ago | lesswrong.com | Michaël Trazzi

This is a special post for quick takes by. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page
Main Insights From The SB-1047 Documentary — LessWrong

1 month ago | lesswrong.com | Michaël Trazzi

Last week I published a 30-minute documentary about SB-1047 I had been working on since September. Here's what I learned. The bill had to go through many committees before passing the California Senate and Assembly, eventually reaching the Governor's deskMost people started paying attention in May-Sep 2024, but the story of the bill starts in September 2023, when Senator Scott Wiener published an intent bill to gather support (co-sponsors), before publishing SB-1047 in February 2024.
5 homegrown EA projects, seeking small donors — LessWrong

Oct 28, 2024 | lesswrong.com | Michaël Trazzi |Gavin Leech |Elizabeth Van Nostrand |Nuño Sempere

What do I mean by “homegrown”?
Finishing The SB-1047 Documentary In 6 Weeks — LessWrong

Oct 28, 2024 | lesswrong.com | Michaël Trazzi

(Some people have messaged me asking me to crosspost my Manifund proposal to Lesswrong for reach. Below, a summary. Full text available here)We will produce a one-hour feature documentary about SB-1047, which would:Serve as a comprehensive reference on the bill's history and implications. Present a balanced view of perspectives from both proponents and opponents, bridging ideological divides. Contribute to informed discussions about future AI Policy by providing in-depth, impartial analysis.
Owain Evans on Situational Awareness and Out-of-Context Reasoning in LLMs — LessWrong

Aug 24, 2024 | lesswrong.com | Michaël Trazzi |Owain Evans

Owain Evans is an AI Alignment researcher, research associate at the Center of Human Compatible AI at UC Berkeley, and now leading a new AI safety research group. In this episode we discuss two of his recent papers, “Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs” (LW) and “Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data” (LW), alongside some Twitter questions.
Evan Hubinger on training deceptive llms that persist through safety training

Feb 10, 2024 | theinsideview.ai | Michaël Trazzi |Adversarial Training

.. 2024-02-11 Evan Hubinger leads the Alignment stress-testing team at Anthropic and recently published “Sleeper Agents: Training Deceptive LLMs That Persist Through Safety Training”. In this interview we mostly discuss the Sleeper Agents paper, but also how this line of work relates to his work with Alignment Stress-testing, Model Organisms of Misalignment, Deceptive Instrumental Alignment or Responsible Scaling Policies.
Statement on AI Extinction - Signed by AGI Labs, Top Academics, and Many Other Notable Figures — LessWrong

May 30, 2023 | lesswrong.com | Michaël Trazzi |Ben Pace |Wei Dai |Alan Dunne

For those who might not have noticed, this actually is historic, they're not just saying that- the top 350 people have effectively "come clean" about this, at once, in a schelling-point **kind-of** way. The long years of staying quiet about this and avoiding telling other people your thoughts about AI potentially ending the world, because you're worried that you're crazy or that you take science fiction too seriously- those days **might have** just ended.