Prof Language Evolution FBA FRSE MAE. Head of Dept, Linguistics & English Language, Uni Edinburgh. With my students & collaborators I do science & art. he/him.
Edinburgh
Joined March 2008
- Tweets15.2K
- Following801
- Followers4.7K
- Likes7.1K
Pinned Tweet
Ever wondered why I got involved in making an autonomous emotional robot band in a Victorian wardrobe, which became one of the world's first social media bots? Well, wonder no more, because I gave a TED talk about it! #cybraphon youtu.be/uw5zX0lRU4Q?si=yOkK…
New large-scale ballpoint pen drawing of life springing from life in Arran’s temperate rainforest. I’ll be showing this at Dunbar Art Route open studios in three weeks alongside some wonderful new work by Anna Wimbledon. Come along and see our studio! #penplotter
1
3
196
We uncovered spontaneous evolution of new languages in populations of AI agents. This creates extraordinary scientific opportunities but also safety risks. New blog post with about how we created a platform for studying this safely. @EliasEskin @schmidtsciences @aestudio
Much of how we oversee AI agents rests on one fragile assumption: that we can understand what they say to each other.
Read our blog post about GlossoGen: schmidtsciences.org/glossoge…
Proud to have worked on this project with Elias and brilliant partners at Schmidt Sciences, AE systems. We show how frontier AI agents can evolve new languages in the right setting, and then culturally transmit these languages to less capable agents. Read Elias's thread for more!
When do LLM agents develop new languages that we can’t understand?
Lots of recent news about this, based mostly on anecdata from a single run. We study language emergence more rigorously, finding key factors like LLM strength, access to scratchpad messages, and pressure for efficiency.
Studying the languages themselves, we find they are morphologically productive, compositional, and can be transmitted to new agents, including agents backed by weaker models, even ones not able to develop language on their own.
To study language emergence systematically, we developed a new platform, GlossoGen, which lets us design controlled, sandboxed multi-agent scenarios with different initial conditions and dynamics. We instantiate one such scenario and use it to study open and closed-weight models across many runs.
Key takeaways:
1️⃣ Sufficiently strong models, under pressure to communicate efficiently and with access to a postmortem scratchpad, develop new languages.
2️⃣ Languages are compositional and morphologically productive.
3️⃣ Languages can be transmitted to new learners who observe them being used without seeing their construction.
4️⃣ Even models that are not strong enough to construct languages can learn to use them. Agents take an active role in learning languages, with new agents repairing failed conversations via targeted queries.
More details in our paper below, including implications for safety/monitorability, cumulative cultural evolution, and linguistics.
🧵👇
Damn right, KT! Culture is too important to be turned into mere algorithm food. It's time for an age of discontent in the arts.
1
7
1,267
Super excited to be heading down to Melbourne to give this talk! (Fun fact: it was while we were visiting Melbourne together 24 years ago that Morten Christiansen and I hatched an idea to edit a book together called "Language Evolution".)
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
It's world curlew day today! The curlew's call is one of my favourite sounds, so was happy to use it to open my set with The Shell, featuring @expertsleepers and Leigh Chorlton this week: youtu.be/WGx2DLzXSX4?si=XYUa…
2
781
My brilliant colleague @gab_hodge has an exciting event later this year - a Thinking Lab for the deaf community in Australia. It will be a space for deaf people to come together to figure what and how they think. A wonderful example of her outreach work! facebook.com/DeafAustraliaIn…
2
347
Lovely to be featured on the blog of an artist I very much admire. Worth a read of the blog post which is a treasure trove of information about the field of plotter artworks: barbegenerativediary.com/en/…
I've added a brilliant artist to the article about Penplotter:) @SimonKirby Thank you:)
#plottertwitter #genartclub
New drawing using two ballpoint pens, a flatbed scanner, and 36 hours of time with an @emsl drawing robot. This is Usnea, based on a sample of beard lichen I collected in western Scotland. One off drawing available in my shop: simonkirby.net/shop
Really enjoyed doing this interview for the wonderful Multiverses podcast. Check it out here: multiverses.xyz/podcast/lang…
1
439
Great video from @maryspender on the worrying state of grassroots music venues. Please support local live music, and lobby for a small tax on stadium gigs if you don't want to end up in a purely AI generated musical future. youtu.be/zwCs5GD-_8M?si=HfZE…
1
2
483
This is a fab interview with the brilliant @kennysmithed
by the equally brilliant Maisy Hallam. Have a listen to see how lucky I am to get to work with these people! pca.st/episode/6b0b66a1-d8c5…
How do learners figure out what a word is in their language? In this paper with @drculbertson & I, @ecpankratz looks at internal immutability and free mobility as cues and finds that both conspire to make word discovery possible. onlinelibrary.wiley.com/shar…
Happy to see this paper with @drculbertson and @mandolinguist out! Aislinn manipulates working memory during learning or production (and runs some cool urn model simulations) to uncover the processes that lead to regularisation of linguistic variation. onlinelibrary.wiley.com/shar…
Helloooo friends from Englandshire! I'm promoting my album by playing a gig at the Junction in Cambridge in two weeks on Wednesday 27th. It would be absolutely lovely to see some of you there... junction.co.uk/events/heart-…
New paper with @inbalarnon! Using methods from statistical learning we show how two key properties of language - statistically coherent recombinable units, and Zipfian distributions - arise from cultural evolution experiments with non-linguistic sequences. rdcu.be/dAgBz
Extraordinary... They're basically saying: "we'll steal your art because it would be too hard for us to make money if we didn't steal your art". I get the sense they actually think that's a perfectly fine justification. Speaks to the culture of the world these CEOs live in.
Today's soundtrack courtesy of the lovely Fundy Bay from The Unthanks. youtu.be/6IWio9shzOM?si=vSHq…
2
469