@jurgjn.bsky.social
Reposted
If you want to implement an AI tutor, you need to study it’s performance in naturalistic settings with the kinds of context windows that student learners will provide. You can’t begin with a well formulated question about a single topic.
Students don’t know how to formulate questions well at first.
Students don’t know how to formulate questions well at first.
October 30, 2025 at 10:54 AM
If you want to implement an AI tutor, you need to study it’s performance in naturalistic settings with the kinds of context windows that student learners will provide. You can’t begin with a well formulated question about a single topic.
Students don’t know how to formulate questions well at first.
Students don’t know how to formulate questions well at first.
Reposted
We’ve now explored this on all GPU models available on our cluster and some non-A100/H100 do not have the issue; seems like something nuanced that can hopefully be fixed:
github.com/google-deepm...
github.com/google-deepm...
Model does not run correctly on non A100/H100 GPUs · Issue #59 · google-deepmind/alphafold3
A note from us at Google DeepMind: We have now tested accuracy on V100 and there are serious issues with the output (looks like random noise). Users have reported similar issues with RTX 2060S and ...
github.com
November 18, 2024 at 11:32 AM
We’ve now explored this on all GPU models available on our cluster and some non-A100/H100 do not have the issue; seems like something nuanced that can hopefully be fixed:
github.com/google-deepm...
github.com/google-deepm...
We’ve now explored this on all GPU models available on our cluster and some non-A100/H100 do not have the issue; seems like something nuanced that can hopefully be fixed:
github.com/google-deepm...
github.com/google-deepm...
Model does not run correctly on non A100/H100 GPUs · Issue #59 · google-deepmind/alphafold3
A note from us at Google DeepMind: We have now tested accuracy on V100 and there are serious issues with the output (looks like random noise). Users have reported similar issues with RTX 2060S and ...
github.com
November 18, 2024 at 11:32 AM
We’ve now explored this on all GPU models available on our cluster and some non-A100/H100 do not have the issue; seems like something nuanced that can hopefully be fixed:
github.com/google-deepm...
github.com/google-deepm...
The former finished without errors, but the output was noise (something similar to 100% spaghetti with AlphaFold2). The latter finished with the structure posted by @pedrobeltrao.bsky.social (2/2)
November 15, 2024 at 8:16 AM
The former finished without errors, but the output was noise (something similar to 100% spaghetti with AlphaFold2). The latter finished with the structure posted by @pedrobeltrao.bsky.social (2/2)
We tried running the example from README.md (“2PV7”) on a lower-end GPU with --flash_attention_implementation=xla (described in performance.md), and on an A100 GPU without that option. (1/2)
November 15, 2024 at 8:16 AM
We tried running the example from README.md (“2PV7”) on a lower-end GPU with --flash_attention_implementation=xla (described in performance.md), and on an A100 GPU without that option. (1/2)