A non-profit AI Alignment organization based out of the UK.
Cambridge, UK
Joined August 2025
- Tweets103
- Following179
- Followers915
- Likes221
Geodesic Research retweeted
A bad day to be a misaligned AI
As Geodesic scales, we're delighted to welcome @n_lie_k as our newest member of technical staff. We can't wait to get to work 🚀
Geodesic Research retweeted
AI safety needs to scale fast.
MATS has trained 10 cohorts of top researchers, but high-impact orgs keep hitting the same bottleneck: more promising ideas than people to champion them, and funding outpacing deployment.
This track exists to close that gap.
Geodesic Research retweeted
I'm extremely excited to bring people on the team who live for making the future of humanity brighter.
If you know anyone who you think would be a good fit (or you think you would be), DM me!
Thanks to a generous philanthropic grant from @coeff_giving (pending final logistics), 𝘎𝘦𝘰𝘥𝘦𝘴𝘪𝘤 𝘪𝘴 𝘩𝘪𝘳𝘪𝘯𝘨 𝘧𝘰𝘶𝘳 𝘔𝘦𝘮𝘣𝘦𝘳𝘴 𝘰𝘧 𝘛𝘦𝘤𝘩𝘯𝘪𝘤𝘢𝘭 𝘚𝘵𝘢𝘧𝘧. Come build the base of alignment with us 🤖
We're a Cambridge-based AIS org. Our seminal work (alignmentpretraining.ai) showed you can bake alignment priors into base models.
Applications now open: airtable.com/appuugUGFPJEy6X…
Geodesic Research retweeted
Great paper on continual learning by @LPacchiardi .
We should be far more prepared for a world where agents learn extensively from their environments. This work seems like a solid starting point and was very helpful for conceptualizing different types of CL systems.
Geodesic Research retweeted
Excited about good people applying to Geodesic; I think they do great work on squeezing out alignment from compute/data-intensive, neglected aspects of the training stack : )
Geodesic is hiring Members of Technical Staff. Come align some AIs with us!
We're a Cambridge-based AI safety org. Our seminal work showed you can bake alignment priors into base models.
Now, we want to make base models robust to the adversarial effects of long-horizon capabilities RL.
EOI (~5 mins): tally.so/r/vG4G6A
Geodesic Research retweeted
This is very important work and the Geodesic team is cracked + extremely nice! Apply apply
Geodesic is hiring Members of Technical Staff. Come align some AIs with us!
We're a Cambridge-based AI safety org. Our seminal work showed you can bake alignment priors into base models.
Now, we want to make base models robust to the adversarial effects of long-horizon capabilities RL.
EOI (~5 mins): tally.so/r/vG4G6A
Geodesic Research retweeted
Come help us solve alignment 👍
Geodesic is hiring Members of Technical Staff. Come align some AIs with us!
We're a Cambridge-based AI safety org. Our seminal work showed you can bake alignment priors into base models.
Now, we want to make base models robust to the adversarial effects of long-horizon capabilities RL.
EOI (~5 mins): tally.so/r/vG4G6A
Geodesic Research retweeted
Geodesic is a new AI safety org i’m particularly excited about: they do awesome neglected work trying to figure out how to shape alignment priors for frontier AI. People should consider applying!
Geodesic is hiring Members of Technical Staff. Come align some AIs with us!
We're a Cambridge-based AI safety org. Our seminal work showed you can bake alignment priors into base models.
Now, we want to make base models robust to the adversarial effects of long-horizon capabilities RL.
EOI (~5 mins): tally.so/r/vG4G6A
Geodesic Research retweeted
Anthropic does a lot of alignment science. This is good, but I also wonder how much the conclusions they draw rely on baked-in assumptions about how they did pretraining, midtraining, etc.
Better open-source alignment needed as a contrast point
Geodesic Research retweeted
We are sharing those early negative results with the hope of sparking more research on how shaping alignment priors generalizes to alignment in realistic settings. We remain excited about other varieties of alignment midtraining that might generalize more robustly.
Geodesic Research retweeted
A lot of engagement s focussing on the effect of AI doomer talk on AIs.
From the paper, it should be clear that filtering doesn't matter, as long as you can upsample the behaviour you *do* want to see.
Shed your preconceptions so we can be AI bloomers together <3
Geodesic Research retweeted
Self-fulfilling alignment? (image credit: @QuintinPope5)
turntrout.com/self-fulfillin…
