Alternatives
Products that do what The “tl;dr” of Recent Transformer Papers does
- 1OP
2017 · github.com
- 2IE
2015 · jackschaedler.github.io
- 3RH
2018 · github.com
- 4AS
2018 · chrisseaton.com
- 5PR
2017 · pdflower.com
- 6CA
2020 · github.com
- 7AS
2018 · deepmind.com
- 8CW
2014 · codewords.hackerschool.com
- 9CG
2023 · github.com
- 10

- 11

- 12WC
2017 · medium.com
- 13AI
My focus has been shifting towards the ML alignment space recently, and in particular the ability to translate large transformer models into human understandable circuits and algorithms. This problem potentially isn't solvable, but it is one that some groups have had success with after large amounts of effort. In attempting to address this issue, I've been developing Transpector. A tool scaling up and reducing the barrier to entry of techniques that these teams have been showing success with. Techniques aiming to understand the internal mechanics of the model. Currently this tool is focused…
2023 · github.com
- 14

- 15

- 16

- 17

- 18

- 19DV
2017 · dvblogger.com
- 20EA
2019 · exbert.net
- 21PC
2014 · github.com
- 22M1
2019 · electricitytransition.com
- 23LP
2020 · github.com
- 24SN
2019 · soliloquy.cc
Ranked by how close each launch is in meaning, then by votes. Refine with a description →