Thanks to a generous philanthropic grant from @coeff_giving (pending final logistics), ๐๐ฆ๐ฐ๐ฅ๐ฆ๐ด๐ช๐ค ๐ช๐ด ๐ฉ๐ช๐ณ๐ช๐ฏ๐จ ๐ง๐ฐ๐ถ๐ณ ๐๐ฆ๐ฎ๐ฃ๐ฆ๐ณ๐ด ๐ฐ๐ง ๐๐ฆ๐ค๐ฉ๐ฏ๐ช๐ค๐ข๐ญ ๐๐ต๐ข๐ง๐ง. Come build the base of alignment with us ๐ค
We're a Cambridge-based AIS org. Our seminal work (https://t.co/htHYaQdOfD) showed you can bake alignment priors into base models.
Applications now open: https://t.co/vkwzyKZ9jU
The UK's sovereign supercomputer team made a video about the research we did on their hardware. It's an incredibly clear overview of our work on Alignment pretraining, and a beautiful piece of media!
Video below โฌ๏ธ
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.
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!
We aim to fill these roles as soon as we find suitable team members โ ๐บ๐ฐ๐ถ'๐ญ๐ญ ๐ฃ๐ฆ ๐ข๐ฎ๐ฐ๐ฏ๐จ ๐ฐ๐ถ๐ณ ๐ง๐ช๐ณ๐ด๐ต ๐ต๐ฆ๐ค๐ฉ๐ฏ๐ช๐ค๐ข๐ญ ๐ฉ๐ช๐ณ๐ฆ๐ด, ๐ธ๐ช๐ต๐ฉ ๐ด๐ถ๐ฃ๐ด๐ต๐ข๐ฏ๐ต๐ช๐ข๐ญ ๐ช๐ฏ๐ง๐ญ๐ถ๐ฆ๐ฏ๐ค๐ฆ ๐ฐ๐ฏ ๐ฉ๐ฐ๐ธ ๐ต๐ฉ๐ฆ ๐ฐ๐ณ๐จ ๐จ๐ณ๐ฐ๐ธ๐ด ๐ข๐ฏ๐ฅ ๐ฉ๐ข๐ด ๐ช๐ฎ๐ฑ๐ข๐ค๐ต.
Apply! ๐https://t.co/vkwzyKZ9jU
Thanks to a generous philanthropic grant from @coeff_giving (pending final logistics), ๐๐ฆ๐ฐ๐ฅ๐ฆ๐ด๐ช๐ค ๐ช๐ด ๐ฉ๐ช๐ณ๐ช๐ฏ๐จ ๐ง๐ฐ๐ถ๐ณ ๐๐ฆ๐ฎ๐ฃ๐ฆ๐ณ๐ด ๐ฐ๐ง ๐๐ฆ๐ค๐ฉ๐ฏ๐ช๐ค๐ข๐ญ ๐๐ต๐ข๐ง๐ง. Come build the base of alignment with us ๐ค
We're a Cambridge-based AIS org. Our seminal work (https://t.co/htHYaQdOfD) showed you can bake alignment priors into base models.
Applications now open: https://t.co/vkwzyKZ9jU
We're looking for technical staff with experience across the ML and alignment research stack:
โข multi-GPU / HPC training and evals
โข deep familiarity with data-centric alignment methods
โข impact-oriented thinking about lab adoption and theories of change
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.
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 a new AI safety org iโm particularly excited about: they do awesome neglected work trying to figure out how to shape alignment priors for frontier AI. People should consider applying!
You'll be among our first technical hires, with real influence on how the org grows and has impact.
EOI is 5 questions, ~5 mins. If it's a fit, we'll follow up about the full application: https://t.co/wzKMxKCmsL
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): https://t.co/aFtv5JWc66
We're looking for technical staff with experience across the ML and alignment research stack:
- multi-GPU / HPC training and evals experience
- deep familiarity with data-centric alignment methods
- an insatiable desire to improve the outcomes of developing superintelligence