Podcast Episodes
Back to Search“A conceptor by any other name” by Keenan Pepper
I just had one of those delightful moments where I have a very specific idea, and then I search for it (Claude Research in this case), and it turns …
3 weeks, 4 days ago
“Some Important Models for Health and Fitness” by benwr
This is a synthesis of many facts I've learned over the last few years, mainly about metabolism and exercise,[1] that have helped me become much hea…
3 weeks, 4 days ago
“Claude Code as a Claude Coach” by Brendan Long
Exercise is hard but it's even harder if you have to use your brain and muscles at the same time. I wish a personal trainer would just teleport into…
3 weeks, 4 days ago
“Bounding eval awareness of ~human-level AI across the safe-to-dangerous shift” by Patrick Leask, Charlie Griffin
In our last post, we argued that measuring evaluation awareness is fundamentally challenging because of the safe-to-dangerous distributional shift: …
3 weeks, 5 days ago
“Desiderata for functional welfare experiments on LLMs” by Rikhil Jhaveri, Jamie Johnson, David Africa
TLDR
LLMs appear to have functional welfare: coherent sets of behaviour that track how well things are going relative to their goals. Improving mod…3 weeks, 5 days ago
“A Review of Anthropic’s Global Workspace Paper” by Neel Nanda
The below is a public review Anthropic asked me to write for their new global workspace paper. I recommend at least skimming their paper first.
TLDR…
3 weeks, 5 days ago
“SFF is very suboptimal” by Zach Stein-Perlman
I recently served as a recommender in SFF's annual funding round (grants will be decided and announced in September). I'm deeply grateful for SFF's …
3 weeks, 5 days ago
“Visioning: Concretely Imagining What You Want” by Gretta Duleba, johnswentworth
When John told me (Gretta) his practice of “visioning,” I was skeptical at first. I gave it a try, a little bit out of spite, to show him I was ca…
3 weeks, 5 days ago
“A global workspace in language models” by wesg
[This is the blog post for our new paper Verbalizable Representations Form a Global Workspace in Language Models
Readers might also be interested in…
3 weeks, 5 days ago
“Sub-agent delegation chaining” by David Rein
Epistemic status: pretty confident in the validity of the core proposal, not that confident in specific implementation details
TL;DR: we should cryp…
3 weeks, 5 days ago