Hi, thanks for this, I did go through this video, I am still unclear about what was their task suite like, my task suite was pretty narrow as i noted in the limitations and was made to elicit only a specific type of behaviour, so it will be interesting to see those parameters in the MATS project and different model families as well activation monitorability as well.
Based on a skim, you may be interested in this MATS project
Hi, thanks for this, I did go through this video, I am still unclear about what was their task suite like, my task suite was pretty narrow as i noted in the limitations and was made to elicit only a specific type of behaviour, so it will be interesting to see those parameters in the MATS project and different model families as well activation monitorability as well.