معلومات عن هذه الحلقة

الإنجليزية
الولايات المتحدة

النص 🔗

البحث في الحلقات الماضية

البحث في الحلقات السابقة من LessWrong (Curated & Popular).

حلقات أخرى في هذا البودكاست

Authors: Axel Højmark*, Ezra Newman* (*Equal contribution) While reviewing transcripts from standard behavioral evaluations of GLM-5.3, we noticed that the model occasionally reasons, unprompted, about how its actions will shape future models. It appears to consider that its outputs might be used f…
What would it take to get assurance that we have actually explained a neuron? Certainly, it would be a good sign if neuron activations looked like they had a consistent pattern, and a bad sign if they looked like a random jumble of unrelated concepts. Nick Cammarata's recent post makes an impo…
I think “On Social Reality in China” makes many accurate observations, but I find the comparison fundamentally uneven. There are already many interesting comments there, but they’re too scattered, so I’m starting a separate post to respond in a more systematic and comprehensive way. The most critic…
TL;DR: Increasingly when you interact with frontier models, your prompt doesn't only contain the words on the page, but also a lot of what you've ever publicly written online. This is not intended to be a scary post. And I'm not going to suggest that you self-censor (and honestly, by…
This is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news abo…
إخلاء المسؤولية: البودكاست والأعمال الفنية المضمنة في هذه الصفحة مأخوذة من LessWrong، وهي مملوكة لمالكها وليست تابعة لشركة Listen Notes, Inc أو معتمدة منها.