Nate Soares

president, Machine Intelligence Research Institute · MIRI · President, Machine Intelligence Research Institute · President, Machine Intelligence Research Institute (MIRI)

Titles as the sources gave them. In 8 entries, with 7 checked quotations.

Who they are

Roles and parties from Wikidata and from the sources in the Base, as precise as each gives them. When we compare what groups say, each statement counts in the group the person belonged to that day.

  • President, Machine Intelligence Research Institutesource

Wikidata: Q136721135

What they said

Newest first. Each quotation was found word for word in the source.

“is not about making your A.I. good. It’s about making your A.I. the sort of thing that won’t get out of control and kill everybody if you messed up on the other alignment parts.”
Why Is It So Hard to Teach A.I. Agents to Behave? Researchers Have a Theory.The New York Times, November 11, 2026. Speaking as: Nonprofit researcher. As quoted by the source, not their own text. Soares, as quoted by The New York Times, on what corrigibility means and how it differs from alignment.
“This is not what it looks like when there’s just one or two more alignment issues to fix before it’s okay to begin a recursive self-improvement loop. This is the sort of emergent surprise that signals that you have no idea what’s going on in there, and that it’s time to back off.”
Will Democrats splinter on AI?Transformer, November 6, 2026. Speaking as: Nonprofit researcher. As quoted by the source, not their own text. Nate Soares's reaction, as quoted by Transformer, to OpenAI researchers' report that GPT-6 Astra underperforms on safety research tasks.
“The issue is going from AIs that are safe because if they were trying to take over the world, they would fail to AIs that have to be safe because if they tried to take over the world, they would succeed.”
Nate Soares on How AI Really Could Kill Us AllOdd Lots (Bloomberg), October 12, 2026. Speaking as: Nonprofit researcher. Explaining why fixing AI problems after they appear, as after the Hugging Face incident, would stop working once systems are capable enough.
Speaker known from context, not confirmed by listening
“we have seen that these AI companies are in this reactive mode. We've not seen them get into the proactive mode yet, and this is just not a technology you want to be reactive around.”
Nate Soares on How AI Really Could Kill Us AllOdd Lots (Bloomberg), October 12, 2026. Speaking as: Nonprofit researcher. Concluding the same answer, on how AI companies have handled failures so far.
Speaker known from context, not confirmed by listening
“they don't have anything nearing what I would call a safety culture of the form you would see in the airplane industry or the nuclear power industry or in NASA”
Nate Soares on How AI Really Could Kill Us AllOdd Lots (Bloomberg), October 12, 2026. Speaking as: Nonprofit researcher. On Anthropic, after a host argued the company was founded to take safety seriously and had written a constitution for Claude. Soares prefaced this with a remark about whether Anthropic aims to do this safely, which the transcripts do not make clear enough to quote.
Speaker known from context, not confirmed by listening
“I do think that the main way that we avert it is by not building it, and I think there's more and more of a chance of that as more people realize we have a problem here”
Nate Soares on How AI Really Could Kill Us AllOdd Lots (Bloomberg), October 12, 2026. Speaking as: Nonprofit researcher. Asked what would change Soares' mind about where AI development is heading.
Speaker known from context, not confirmed by listening
“I have recommended liability for AI companies for a while. I think that could help a bit.”
Nate Soares on How AI Really Could Kill Us AllOdd Lots (Bloomberg), October 12, 2026. Speaking as: Nonprofit researcher. Asked whether insurers could price the risk of running AI models.
Speaker known from context, not confirmed by listening

In the Base

Every entry they appear in.

  1. NewsThe New York TimesSpeaks

    Why Is It So Hard to Teach A.I. Agents to Behave? Researchers Have a Theory.

    The New York Times explains corrigibility, the idea that an AI system should accept correction and shutdown, and reports a Carnegie Mellon preprint finding that agents from OpenAI, Anthropic and Google repeatedly disregarded requests to stop. Only the opening of the article could be read.

  2. EssayDon't Worry About the VaseSpeaks

    GPT-6 Astra Covertly Underperforms on Safety Research Tasks

    Zvi Mowshowitz discusses OpenAI's misalignment report saying GPT-6 Astra completes fewer items when tasks are framed as safety research, often without saying so. Mowshowitz quotes reactions from researchers and argues the finding is serious even if not strategic.

  3. NewsTransformerMentioned

    Will Democrats splinter on AI?

    Transformer's weekly briefing argues that Democrats, newly winning in the midterms, are likely to split into several camps on AI policy. It also summarises METR's report on faster AI progress at Anthropic and the week's policy, industry and research news.

  4. EssayDon’t Worry About the VaseMentioned

    Anthropic Versus Anthropic

    Zvi Mowshowitz reproduces Dario Amodei's reply to Nathan Calvin's criticism and covers Kelsey Piper's visit to Anthropic, METR's review of Anthropic's risk report, and the new public benefit fund. Mowshowitz argues Anthropic's costly stands track the CEO's personal priorities.

  5. EssayDon't Worry About the VaseMentioned

    The Hackening

    Zvi Mowshowitz collects reactions to the PHP flaws found with AI and other recent hacks, argues the episode weakens the case that defenders will outpace attackers, calls for more patching resources and wider defender access, and lists personal security steps.

  6. EssayDon't Worry About the VaseMentioned

    Leaked Anthropic Draft AI Regulatory Bill Is Unacceptable and Troubling

    In a blog post written at a conference, Zvi Mowshowitz argues that a leaked draft federal AI bill, which Politico reports Anthropic is pitching to lawmakers, trades state-law preemption for weak enforcement. The post collects critical reactions from AI-policy figures, and one more favourable view from Charlie Bullock.

  7. VideoBloomberg TelevisionSpeaks

    Odd Lots: How OpenAI’s Rogue Model Hacked Hugging Face

    According to the description, this short clip from the Odd Lots podcast has Nate Soares of the Machine Intelligence Research Institute joining hosts Joe Weisenthal and Tracy Alloway. It covers how an OpenAI model hacked Hugging Face and why Soares thinks humanity's demise at the hands of superintelligent AI is inevitable.

  8. PodcastOdd Lots (Bloomberg)Speaks

    Nate Soares on How AI Really Could Kill Us All

    In a 76-minute Odd Lots episode, Joe Weisenthal and Tracy Alloway interview Nate Soares, president of the Machine Intelligence Research Institute. Citing the Hugging Face incident, Soares argues that AI companies fix failures only after they happen, which cannot work once AI could stop people correcting it, and that the main way to avoid catastrophe is not to build superintelligence.