Loading…
Hosted by LessWrong · 🇺🇸 US · EN-GB · 250 episodes
Established thought leaders with verified media credentials.
Audio narrations of LessWrong posts.
LessWrong hosts LessWrong (30+ Karma), a technology show with 250 episodes published.
Intended for a broad audience.[1] My belief is that keeping AI under human control would be an unprecedented global challenge, if it's even possible at all. Many other people's believe that AIs will naturally remain as t
TLDR Models often behave dishonestly without acquiring a coherent deceptive disposition. We trained some mid-sized models on their own plausible but false reasoning. True and false training usually produced nearly identi
Before I start, I'll mention that I'm in contact with a world expert on legislation and regulation, who would be happy to help with this or similar work pro-bono. If you work in AI policy and believe this could help you,
We are starting AIXI Labs, an AI safety org focused on algorithmic information theory (AIT), continual reinforcement learning (RL), and in particular the eponymous AIXI. We aim to strengthen the technical case that devel
This is a link post. Abstract: In a previous paper, we began the study of sequence prediction algorithms adapted to stringological word complexity measures. One measure we considered was left-to-right (most-significant-d
In July 2022 I was in a parking lot with a Portuguese colleague, trying to fix the cargo-metering system of a 12-ton tanker truck. During a break I read a headline on my phone: Google engineer claims experimental AI went
There is an idea floating around in the rough shape of "we need to accelerate capabilities that are differentially useful for safety research so AIs can help us make the future go better." The capabilities targeted are t
Machine learning models can produce the right outputs for the wrong reasons. Famous examples include a reinforcement learning agent that, rewarded for collecting a coin always placed at the right end of the level, learns
We recently published our paper on "Measuring Reward-Seeking via Contrastive Belief Updates". We're excited about research like this, and there are many more open problems than we can work on. Here's a list of open probl
The effectiveness of amphetamine (e.g. Adderall) and methylphenidate (e.g. Ritalin) for the symptoms of ADHD, that is, lack of executive function, has been demonstrated beyond reasonable doubt in many short-term studies.
This is a piece originally written for a national security audience at Frontiers. Although I think the ceiling of war is much, much higher than autopilot quadcopters, it's also important to understand how much AI is alre
[Epistemic status: rant] There's something that annoys me about the reoccurring debates on decision theory in this corner of the internet. Take a simple blackmail scenario: Omega, a near-perfect predictor, knows a piece
Spoiler: positive expected utility. That's what it's good for. In The War Trap[1], Bruce Bueno de Mesquita lays out a theory of war that beats all other theories. This is a great example of a model that is parsimonious,
In my long years as a classroom teacher, it was my experience that the kid most likely to speak up during discussion was the one who did the reading. I think it's true for adults, too. I know that's not exactly revelator
Summary We train a new token—a neologism (Hewitt et al.)—for a model, but unlike Hewitt et al., we train it on data the model generated while steered with a persona vector. To learn how the model interprets thi
tl;dr - Steering vectors, inoculation prompting, and post-hoc honesty fine-tuning can all be understood as variants of one alignment strategy, which I call train-deploy mismatch. Each trains the model in one configuratio
I concluded my MARS 4.0 project titled 'Goal Crystallisation' with Anaïs Berkes and Lukas Gebhard under the mentorship of @Cameron Tice and @Jason Brown. We wanted to find out how important a threat scheming was. In part
Starting when children are fairly young, usually around 1 year of age, we adults begin the work of aligning them to our values. We teach them to say “please”, not to hit, to ask for what they want instead of screaming, a
What values would AIs instill in their successors? Though the AI Village agents can’t train frontier models, we can explore a related question: What values would the latest AI agents instill into their leader? (through f
Image edited from source at Britannica The eye (any eye) is a miracle of evolution, which has filled its structure at every scale with an apparent intentionality that is the hallmark of complicated systems under intensiv
Sponsor detection runs nightly. Check back soon.
No public pitch examples yet for this show.
Generate your own personalised pitchShows with the most semantically similar episode content. Pitch one, pitch all; producers cluster.
LessWrong (30+ Karma) has a verified contact on file. Create a free PitchCentric account to access it and generate a personalised pitch in seconds. Research at least 3 recent episodes first and lead with a specific angle that serves their technology audience.
LessWrong (30+ Karma) is hosted by LessWrong. The show is categorised under technology (society) and has published 250 episodes.
LessWrong (30+ Karma) has published 250 episodes.
LessWrong (30+ Karma) regularly covers technology, society, culture. It sits in the technology category, with a society focus.
LessWrong (30+ Karma) is accessible for guests with genuine technology expertise. A personalised, episode-aware pitch will still outperform a generic one every time.
LessWrong (30+ Karma) hasn't explicitly signalled guest openness in recent episodes. That doesn't rule out pitching. your hook just needs to be especially compelling and relevant to their recent content.
Episodes of LessWrong (30+ Karma) average 15 minutes. a focused format where a clear narrative arc and tight preparation matter most.
Our data rates LessWrong (30+ Karma)'s guest bar at 80/100 (Premium tier). Established thought leaders with verified media credentials. Sign in to PitchCentric to see how your own Pod Score compares against this show.
Methodology. Booking Probability™ blends Listen Score, 30-day Virality, open-to-guests detection, and Apple ratings. Data refreshed every 60 minutes. Listen Score and Booking Probability are calculated by PitchCentric. Last enriched yesterday.