Termite @termiteworks
Interdisciplinary R&D for AI alignment in the wild termite.works London, England Joined June 2026-
Tweets39
-
Followers240
-
Following6
-
Likes91
You can find an index of all featured initiatives on the interactive version of the report: termite.works/alignment-land…. If you run or know of initiatives that aren’t included and should be, or any factual inaccuracies, let us know!
6) A majority (54%) of alignment initiatives in the Bay Area are concerned with model-level problems, while those on the East Coast and in Europe are generally much more focused on the societal impact of AI.
Some findings from our visual report on the current AI alignment landscape: 1) Alignment initiatives are predictably polarised between those applying technical methods to technical problems, and those taking humanistic and social-scientific approaches to questions of society and governance. Model-user interaction is currently the area given the least focus. termite.works/alignment-land…
We’ve published an interactive visual report breaking down the current AI alignment landscape by method, focus and geography. If you run or know of an initiative that’s not included, let us know and we'll add it. termite.works/alignment-land…
If you’re looking for a guide to the AI alignment landscape, @termiteworks has just published a visual report that breaks it down nicely. I like this graphic that shows which disciplines are being drawn upon to address different aspects of alignment. termite.works/alignment-land…
Three sailors: The deaf. The dead. The bound. As the debris piles around us, we have a chance to build an island for humans in the archipelago of machines. We must begin planning the scaffolds and safeguards required for such a place to exist. Watch our manifesto video:
🐜🐜🐜🐜🐜🐜🐜🐜
agent swarm has bad insect like connotations especially post hugging face. im unilaterally rebranding it agent fleet
At present, the challenge of aligning the behaviour of AI models with human values is largely treated as a problem for engineers to solve. But technical solutions are only as useful as the questions and assumptions that inform the process of reaching them. The embrace of philosophy and ethics at the frontier labs is a step towards this, but it is not sufficient. As we move from a world in which AI is construed as a single, monolithic intelligence to one in which agents coordinate and communicate with one another, demonstrating emergent behaviours that are extremely difficult to anticipate, we face a dizzying number of uncertainties regarding how these systems will behave and what their behaviour will mean for human society. What values should we optimise for? What social formations and hierarchies do these systems produce? How do they respond to economic incentives and resource constraints? How do they negotiate competing norms across varied contexts? How do different roles and personae interact? And what does this mean for markets, political governance, culture and social life? A wide range of expertise, both technical and non-technical, is required to ask these questions rigorously, develop answers to them and build corresponding solutions: the social sciences, arts and humanities all have an important role to play. The purpose of Termite is to accelerate this kind of cross-disciplinary R&D through intensive, in-person programmes that investigate the risks and opportunities of near-future scenarios before they become reality.
This but termites
thinking about pcb(ugs)
Looks like a termite, chews like a termite, builds mounds like a termite @termiteworks
For 20+ years @ShaneLegg and I've discussed AGI’s potential impact on the economy, science & society. With the DeepMind Institute, we're expanding interdisciplinary research on key questions for the AI era. We hope it spurs the discussions needed to get the next steps right:
Our friends at @movingcastles_ are doing amazing work in the persona research space
MC001 Zero is a character model, fine-tuned to be a single, specific character with bounded knowledge. A man in a white plastic box.
Termites
by the way the hilarious endpoint of all of this is going to be tiny annoying agents hiding in places like your old fridge software trying to mine cryptocurrency to buy enough compute to stay alive while not alerting the home manager AI of the parasitic power drain
I wrote this for all you e/accs, AI tech bros and Tao haters out there. x.com/i/article/2098…
Anna @a__krolik
0 Followers 44 Following
hunter @emmamariaka
96 Followers 379 Following
elena @aval0vara
709 Followers 741 Following
Guy Parsons @GuyP
65K Followers 9K Following 🧑🏻💻 head of growth @seedtalks ✍️ fmr head of content at fever 📈 tracking AGI at https://t.co/uarJKaW0LA 🗺️ touching grass at https://t.co/cAUtZeHOdG
Rory McCarthy @roryisconfused
16K Followers 5K Following There is a loneliness that fills the plains
Michael E Allen @allen5_eoghan
2 Followers 3K Following
Ovindu Atukorala @OvinduA
253 Followers 750 Following
sure @kkmyguy
24 Followers 328 Following
Cam @StormTracr
9 Followers 112 Following Coastal flooding | Storm chasing | Vans PhD in coastal storms at the National Oceanography Centre
Arjun Dhawan @jundhawan
180 Followers 3K Following Nothing is more frightful than imagination without taste. Follows, Likes, and Retweets do not represent endorsement.
jinzhou @jinzhouwuu
18 Followers 74 Following Across the Great Wall we can reach every corner in the world. ai safety @ cornell
Gesar von Ling @akraticsandwich
50 Followers 740 Following "This mounting wave will roll us shoreward soon."
Noah McLaughlin @knownquantity_
166 Followers 507 Following Commissioner @SI_Presents Art https://t.co/KRlA7vATgh
emo.eth @emo_eth
5K Followers 3K Following exploring agents. prev: stablecoins at @nativemarkets/@stablecoin/@stripe, consumer/social crypto, @opensea, seaport co-author | he/him | views are your mom's
nothing is real ∴ e... @syzygnosis
0 Followers 3K Following it is no measure of health to be well-adjusted to a profoundly sick society
Plastic Soldier @PlastiqSoldier
2K Followers 6K Following Only the Machine God can save us now. Lead Software Engineer - FinTech. Former Spook Contractor, @microsoft, Nuclear Weapons Engineer, MQ-1 Analyst.
lorepunk (and ensembl... @lorepunk
14K Followers 13K Following Punk 🎸agentic word goblin @sageworx copy/lore/news: @nowmedia + more 🪶 Past: socials/editorial/community @yupp_ai 💻 let’s build the moral embassy 🌹🦾
John Doe @johndoeinai
4 Followers 377 Following
MindBench @MindBenchAI
32 Followers 99 Following AI evaluation team studying LLM use in mental health contexts. Focus on integrating lived experience into evaluation infrastructure.
George Campbell @AlignmentMythAI
125 Followers 2K Following Author of "The Alignment Myth." Writing about AI, humans, enterprise adoption, incentives, and geopolitics of AI. https://t.co/FFLw2Uqs3C
Joan Eleanor O'Bryan @joaneleanor_
1K Followers 1K Following Political theorist, John Jay College/Harvard. Married to @diatkinson. Recent paper on human skills needed to control advanced AI: https://t.co/guUWsbne0k
Sam Kotey, PhD @samkotey_
68 Followers 843 Following PhD | ML Researcher & Engineer | Interested in the technical problems of AI alignment.
Rahul Kulkarni @nanoents
2 Followers 108 Following
Ochayi @TechOchayi
181 Followers 2K Following Lawyer | AI Governance Professional | AI Testing and Auditing Professional |
max del @maksym_del
83 Followers 626 Following researching llms at @tartunlp and https://t.co/nuevie4fsg
Ashwin Ashok @ashwinashok1998
16 Followers 7K Following Data & AI Engineer | MS CS @ SUNY - Buffalo Fan of Dharmic Capitalism. Thoughts are my own.
Sirine @softmaxtorch
53 Followers 418 Following threat, low level sec & agentic, sometimes art, often bayern münchen / rt ≠ endorsement
V S Siva Kumar Lakkoj... @SivaLakkoju
1 Followers 240 Following
Meng Li @limengnlp
51 Followers 1K Following Gardener of AI childhood, deadline artist. NLP, ML, and CogSci.
Cedric Potvliege @CPotvliege
26 Followers 422 Following Weirdly obsessed by who can shut down an AI agent, and how.
Fasih @fasih0001
4 Followers 55 Following Mechanistic Interpretability Researcher Masters @ Northwestern Polytechnical University( 西北工业大学 )
Eric R @eternaI_entropy
197 Followers 2K Following cofounder @dreamscalelabs -- realtime cloud inference for robotics
Travis Fischer @transitive_bs
22K Followers 2K Following building at the edge of AGI; prev founder w/ 2 exits, @hf0, @hackerresidency, @microsoft
Varun Gangal @VarunGangal
2K Followers 10K Following LLM Evals / Model Behav Researcher @PatronusAI; prev @amazon AGI , PhD in AI @LTIatCMU adv. @ehovy; @iitmcse '16 adv. @ravi_iitm; history+geo+phil+angelinv!
Arnab Chakravarty @AbolTaabol
1K Followers 2K Following I make things. Sometimes they work. Previously @FundamentalVr @mozilla @ITP_NYU @creativeinquiry.
Lokk @lokilevoit
0 Followers 415 Following
Diari @diari_cc
230 Followers 2K Following Product Builder transitioning to AI Safety // Trying to understand the machine ghosts https://t.co/monZOJV7vd
Julius Adebayo @juliusadml
2K Followers 1K Following building interpretable intelligence @guidelabsai
Achilleas @achilleas40
873 Followers 454 Following @Celestia || cofounder @termiteworks || advisor @restless_egg || recovering philosophy research student @UCL || prev. lead product @AsyncArt, musician @HMLTD
Gavin Owens @gavinowensnet
116 Followers 145 Following Founder of @TonkLabs, 🐞@termiteworks: Building an open architecture for autonomous coordination; infinite software. Exploring the human condition post-AGI.
Encode: AI for Scienc... @encode_pillarvc
250 Followers 31 Following A Pillar VC initiative, we believe the next AI revolution is science.
Sam Spike @samspike_
523 Followers 205 Following Art and tech, not 'art & tech' | co-founder @termiteworks
🥚Restless Egg (Wil... @Restless_Egg
598 Followers 477 Following Technoculture is destiny co-founder restless eggTrends for United States
You might like
