Search: “safety”

Gary Marcus, a prominent AI researcher and critic, shared a post on X directing followers to learn more about his perspectives on artificial intelligence. The post likely promotes his work, writings,

Gary Marcus critiques common misconceptions about AI, presenting seven corrective perspectives on prevailing beliefs about artificial intelligence's capabilities and limitations. The post likely addre

If leading AI companies are indeed approaching the point of recursive self-improvement, a coordinated, verifiable, and universally applied pause is probably the only responsible solution to mitigate s

Gary Marcus argues for a specific rationale supporting a potential OpenAI bailout, though the exact reasoning is not detailed in the available information. Given Marcus's background as an AI researche

Every action that I partake is animated by two ideals: Truth and freedom. Seeing the endless attacks on both ideals throughout the West is soul-crushing. We did not lose a war of aggression. We decide

The OpenAI Foundation is doing a lot of wonderful things. Helping society become resilient to AI is going to be incredibly important. Much more to come here! AI is advancing quickly. Society’s ability

Gary Marcus critiques Anthropic's claims about their AI capabilities, likely contrasting inflated marketing promises with the actual technical limitations and performance of their systems. The post pr

An OpenAI insider (@thsottiaux) raises concerns about the risks of over-relying on AI agents to handle cognitive tasks, warning against wholesale delegation of thinking to autonomous systems. The warn

The road to Hell is paved with closed-source citadels disguised as good intentions. The Pope is right: AI takes on the characteristics of those who build it, finance it, and regulate it. So the questi

👇@davidSacks raises some interesting points here, which deserve an answer, but arguably gets the solution exactly backwards. Are we not now already leaving unelected private companies precisely the ab

Gary Marcus discusses how alignment instructions in large language models often fail to work as intended, and argues that the emotional attachment some people develop toward LLMs can create additional

Eight key points from the most recent essay in the “AI as Normal Technology” series by @sayashk and me. Do AI Risks Require Extraordinary Government Intervention? 1. There is general consensus that AI

Gary Marcus notes that researcher @thestalwart has found more recent AI models to be less vulnerable to certain attacks or exploits, and suggests that a comprehensive study across multiple models woul

⚠️👇 🚨Breaking ⚠️ If we can’t make AI agents follow rules, we are screwed. New study from METR reports that “when the agents were faced with hard tasks, they routinely violated constraints” This—routin

For a long time, academic researchers being at the cutting edge of new technologies has been a great social equilibrium. Neutral, unbiased technologists have been the people to spread new ideas to the

What we find most useful about CNA is that the intervention is simple yet powerful. The steering is a multiplicative ablation on a sparse set of MLP neurons, which makes CNA a clean addition on top of

What I am about to describe ain’t AGI; it’s a sign of a trillion dollar trainwreck. If I had told you in 2022 that the 2026 version of GPT (which by the way would only be GPT 5.5 and not GPT-6 or 7 li

Interesting position paper on agentic AI as a foreseeable pathway to AGI. (bookmark it) There has been strong debate on whether a larger single model get us there or a multi-agent system. The authors

there are many agent use cases locked behind 'what if' fears because after we give a tool to an agent, we're relying on the prompt to limit behavior tools like @denieddotdev allow teams to manage capa

There will be no AI jobpocalypse. The story that AI will lead to massive unemployment is stoking unnecessary fear. AI — like any other technology — does affect jobs, but telling overblown stories of l

The human brain🧠 is incredibly efficient because it only activates the specific neurons needed for a thought. Modern LLMs naturally try to do this too (> 95% of neurons in feedforward layers stay sile

Gary Marcus is an AI researcher and public intellectual who frequently shares commentary and insights about artificial intelligence developments on social media. His posts on X (formerly Twitter) cove

I'm really excited about this as a new tool in our interpretability tool kit In a new paper, we present NLAs, an unsupervised method for converting an LLM's internal state into human-readable text. I'

This post discusses the dynamics of artificial superintelligence (ASI) development as a competitive race, arguing that competitive pressures make it difficult to slow progress until a critical inflect

Terence Tao recognized that plausibility and veracity are not the same, and that current tools are better at the former than the latter. [edit: the video is from 2024, and affirms what i said in 2019

The crux of the Musk-OpenAI trial so far is that Brockman keeps acting as if selling chatbots and API access for profit (which is what they do now) is exactly the same as the original mission (which w

i love the recent explosion of interactive data visualizations. more plz Who actually shapes AI policy in the U.S.? We mapped 1,812 entities: 745 people, 918 organizations, 2,925 relationships. Fronti

This post discusses the liability and accountability questions that arise when problems occur in AI-automated workplaces, exploring who bears responsibility—whether the AI developer, the employer, the

// Latent Agents // Multi-agent debate makes models reason better. It also burns tokens generating long transcripts before any answer comes out. This new research distills the entire debate into a sin

Gary Marcus discusses technical and security issues affecting the X platform, including malfunctioning polls, compromised accounts, and increased phishing scams in direct messages. The post appears to

Scam Altman didn’t tell the OpenAI board that he OWNED the OpenAI Startup Fund. Altman lied in congressional testimony that he didn’t have financial gain from OpenAI. Ex-board member of OpenAI calls S

Gary Marcus made a critical commentary on Sam Altman's priorities, using a pun on 'AGI' (Artificial General Intelligence) to suggest that Altman's actual focus is on 'Adjusted Gross Income' rather tha

The people building the most powerful technology in history cannot tell you what is happening inside their own systems. This is insane. We started the Torchbearer Community for exactly this reason. Re

Gary Marcus, a prominent AI researcher and critic, posted a message on X (formerly Twitter) addressing software engineers and coders, likely discussing technical aspects of AI development, programming

Existential risk mongers are a small, very vocal cult with a lot of very clever online astroturfing skills. Politicians never waste a good fake crisis, which is why they're perfect for Bernie to try t

What if I told you there was a technology where 1.5 million people would die every year and injure 50 million would you sign up for that tech? Hell no, right? But the answer is actually 'hell yes' bec

In 1982, Blade Runner was speculation. In 2026, it's the conversation. Memory, personhood, alignment, what we owe the minds we build. Watching it Thursday 28 May, Kensington Central Library. Come thin

Rivian and Volkswagen Group's joint venture put Devin to work on testing and ticket triage across a software platform that will power up to 30M vehicles. Devin handles autonomous ticket triage in Slac

If you are inclined to take @ohabryka on his word on issues like this, you may want to know some context... Oliver accuses me and ControlAI of telling people to be more coy about extinction risks. I h

Lyft built 8 agents that resolve 35% of customer issues end-to-end. That stat sounds crazy, but it's the kind of numbers you see when teams actually close the evals feedback loop. Looking forward to I

Is a 92% “honest”* AI really good enough? Or a disaster waiting to happen? —- *”honest” is itself a misleading anthropomorphization of the kind Anthropic loves to promote. “Accurate” would be more acc

Maybe because of this paper? https://x.com/emollick/status/1991624198855561508?s=20 Tell all the truth but tell it slant— Success in Circuit lies Too bright for our infirm Delight The Truth's superb s

🇧🇪 Positive news for FSD Supervised in Belgium! I just received an official response from the cabinet of @MDiependaele , Minister-President of the Flemish Government. A few days ago, the Dutch vehicle

This is what a black politician in South Africa said… “We will kill white women, we will kill white children, and we will even kill your pets' Violent language entering politics is a serious warning s

Jan Leike praised collaborative work by researchers Jiaxin Wen, Liang Qiu, Joe Benton, and Jan Kirchner, directing followers to an Anthropic blog post for further details. The post appears to highligh

Here's my first drive on Tesla FSD V14.3.1. It feels polished vs 14.3 and it my opinion is ready for wide release. • With 14.3.1, you can now tap on the new 'P' parking icon and bring up your differen