Gary Marcus

In other times in history when we have faced uncertainty and powerful new things that may be both good and bad, that are dual use, we have made new organizations, as we have, for example, around nuclear power. We need to come together to build a glob... more Verified source

Algorithmic transparency. When a driverless car has an accident, or a consumer’s loan application has been denied, we should be able to ask what’s gone wrong. The big trouble with the black box algorithms that are currently in vogue is that [nobody] ... more AI Verified source (2024)

OpenAI has also said, and I agree, “it’s important that efforts like ours submit to independent audits before releasing new systems”, but to my knowledge they have not yet submitted to such audits. They have also said “at some point, it may be import... more Verified source (2023)

Ultimately, we may need something like cern Global, international and neutral, but focused on AI safety rather than high energy physics. Unverified source (2023)

A moratorium on Statewise regulation of AI was and is, a terrible idea, especially in a world in which there is no coherent Federal response to AI. [...] A call for federal AI standards in lieu of state standards only makes sense if there are (sensib... more AI Verified source (2026)

It should be obvious that applying hallucinatory and unreliable generative AI to weapon systems without humans in the loop could be catastrophic. [...] Paraphrasing a button that I used to wear as a teenager, one hallucination could ruin your whole p... more AI Unverifiable source (2026)

Everybody, even Google, seems to be treating AI as if it were some kind of winner take all competition like web search was [...]. But everybody is building essentially the same technical solution with essentially the same data, so there is no moat. I... more AI Verified source (2026)

Plot the same improvements on a linear y-axis and you get steady incremental gains, impressive but not the hockey stick that triggered the panic. [...] We don't have evidence that Mythos is actually an important step towards broad superintelligence. AI Verified source (2026)

I think if you asked those questions you would say, well what society most needs is automated scientific discovery that can help us actually understand the brain to cure neural disorders, to actually understand cancer to cure cancer, and so forth. If... more AI Unverifiable source (2017)

My opinion is that the moratorium that we should focus on is actually deployment until we have good safety cases. I don't know that we need to pause that particular project, but I do think its emphasis on focusing more on AI safety, on trustworthy, r... more AI Verified source (2023)

There's a problem in the industry called the alignment problem. How do you get a machine to obey instructions basically, and ideally make it compatible with humans. And so far, we've made almost no progress on that. [...] We as a field have made almo... more AI Unverifiable source (2026)