Cédric

building open-ended autotelic agents
& making little art projects

[Cédric @cedcolas]

and can possibly be adapted to bigger / continuous goal spaces

It was great collaborating with the @FLAIR_Ox lab and @mitrma!

[Cédric @cedcolas]

We looked into the weeds of hindsight experience replay and came up with an efficient way of learning from all goals at once in off-policy goal-conditioned RL!

It works well for reasonable numbers (100s--1000s) of non-exclusive sparse reward goals

[Michael Matthews @mitrma]

Hindsight Experience Replay has become the ubiquitous method for goal-conditioned reinforcement learning, but leaves open the question of which goal to relabel with.

In this work, accepted at ICML, we propose instead simply Learning Everything All at Once (LEO).
1/

[Cédric @cedcolas]

@simonsarris and cambridge doesn't have great food either..

[Cédric @cedcolas]

was not expecting this colab :o
makes me wanna do another postdoc..

[Sydney Levine @sydneymlevine]

@mmuthukrishna and I are hiring a postdoc to join our labs at NYU!  We're looking for someone excited to work on one of society's newly emerging and potentially generation-shaping challenges: the multi-agent alignment problem.

[Cédric @cedcolas]

@jonnym1ller just saw this: https://t.co/mMpE9FdCiG
and some people seem to praise it

(haven't tested myself)

[Aqua Voice @aquavoice]

Aqua Voice is now live for iOS.

It's a premium voice keyboard for every app on your phone.

[Cédric @cedcolas]

@RichDecibels love this!!! it makes me wanna hunt for new places and add them on the map

[Cédric @cedcolas]

can Claude self-report an injected emotion with neutral context? can it detect the mismatch between the emotion and the context (why am i feeling like this?)

seems related to the introspection study: https://t.co/TQqqt2QUjb

what other mental states could we do this with?

[Anthropic @AnthropicAI]

New Anthropic research: Emotion concepts and their function in a large language model.

All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.

[Cédric @cedcolas]

w/ Tracey Mills, Ben Prytawski,@mhtessler, @noahdgoodman, @jacobandreas, Josh Tenenbaum

Paper: https://t.co/tDZsgL2wDN
Play the games here: https://t.co/anWBZVvYNW

[Cédric @cedcolas]

New paper at ICLR 2026! 🎉

"Language and Experience: A Computational Model of Social Learning in Complex Tasks"

We model how humans combine advice from others with direct experience to learn new tasks, and show this enables bidirectional human-AI knowledge transfer.

🧵⤵️

[Cédric @cedcolas]

Can knowledge accumulate across generations?

We run iterated learning chains: each agent gets only 2 lives, then passes advice to the next

Performance increases across generations: partial knowledge compounds through language, mirroring cultural evolution in human populations

[Cédric @cedcolas]

@RhysSullivan i will open source soon, so you can set it up for yourself

[Cédric @cedcolas]

@RhysSullivan not all the way there but i just setup a three way interaction between a telegram bot, obsidian and claude code

so you can chat with claude code about your notes from your phone via telegram, send it links and pdfs to process and it can co-manage your obsidian

[Cédric @cedcolas]

@paularambles they are the claudettes