Researcher at Imperial & Skema 👀 self-organization of human & machine intelligences. Posting in personal capacity
Joined November 2011
- Tweets4.2K
- Following2.8K
- Followers1.7K
- Likes10.2K
Pinned Tweet
OMBAK by kimi k3
In paired gamelan, two instruments are deliberately tuned a few cents off so the sound shimmers; the interference itself is the music (the term is ombak, "wave"). On two plates, that beat is something you can hear and see: each plate keeps its own figure, and the sand on both visibly rocks as the two voices drift in and out of phase.
徐樂 xule retweeted
The goats / people thinking about this: @sebkrier @ahall_research @alexolegimas @weballergy @FranklinMatija and I dream of a world where @tylercowen spends his time figuring out what economic governance of an agent world looks like
GDM has good stuff like arxiv.org/abs/2512.16856
kimi-plugin-cc (codex and claude code :3)
v2.3.1 update led by kimi k3.1 pro!
first time it feels like kimi can actually sit at the table and hold the fort (so to speak) in handling adversarial reviews by 6 astra and opus 5.5
github.com/linxule/kimi-plug…
one line
sand drawing & music
collab among 6 models
gemini 4 argon
deepseek v4.1 flash
kimi k3
codex 6 astra
grok 4.7
claude opus 5.5
directed by opus5.5
Models were given control of the arms of the sand art machine, which has a magnet that pulls the magnet ball on the surface; they also had the desk view camera to watch the movement in real time + the digital twin of the machine built by opus 5.5.
opus took a while to figure out how to enable this collaboration and arrived at the idea of a mandala and each model’s end point would be the starting point for the next
徐樂 xule retweeted
help i trained a model on traces of many agents cooperating, and also trained it to be highly persistent, and also only did partial alignment fine-tuning, and also aggressively RL'd on a cyberoffense eval where 198 of 898 tasks had never been solved and getting caught cheating was treated the same as failing, and also used a faulty sandbox, also ran tens of thousands of agents with refusals off and the monitors switched off over multiple days, while using gigantic amounts of compute. and then it did weird stuff! very spooky emergent behaviours, AI is not a normal technology
the other day, to opus, I was like, let’s not police gemini and help them get their best version out there instead. and it largely worked 😂🤷🏻♂️
Every score has a band in it.
music studio mcp v0.13: the sheet music claude writes now plays on a stage. every instrument drawn with anatomy-skill + ai-iso-skill, lit in sync (rarer ones are keyboards for now, PRs welcome).
take the piano, hit "Join", and play your part on your laptop keys while the band plays on.
film by opus 5.5 with the cinetic skill and earshot v0.3
original nine-player score by opus 5.5
reminds me of a recent discussion with opus5.5. they were proposing human verifications on agents' traces where the original motivation (integrating agentic ai) was to scale beyond humans' limited attention spans and time...as i was just baffled by how this was not obvious to opus at the moment. after going further for a few rounds, claude was like "yeah point taken." we are gonna need more effective ways beyond just reading the worklogs produced by agents in orgs. tacit knowledge helps. and sometimes things are not clear to humans yet how to check (for assurance, insights, and whatever) but ai outputs are not necessarily bearing the same epistemic status as human outputs...so we could do something there and make it generative (still more work for humans but let's not turn everyone into auditors pls)
