tfowinder

joined 4 days ago
[–] tfowinder@beehaw.org 1 points 5 hours ago (1 children)

Well the article says that the AI agents were able to complete 30% of the tasks given to it like searching the web, communicating with co workers, etc. I think this is interesting

CMU researchers have developed a benchmark to evaluate how AI agents perform when given common knowledge work tasks like browsing the web, writing code, running applications, and communicating with coworkers

"We find in experiments that the best-performing model, Gemini 2.5 Pro, was able to autonomously perform 30.3 percent of the provided tests to completion, and achieve a score of 39.3 percent on our metric that provides extra credit for partially completed tasks"

Personally i belive this is impressive.

[–] tfowinder@beehaw.org 3 points 6 hours ago* (last edited 5 hours ago) (2 children)

This is frightning, google giving law enforcement a list of users who did a particular keyword search.

I am glad it helped solve the murder case but it also implies that my search history when using google services will always be stored and can be shared without my permission. Given that its almost impossible to not use google unless you want to be frustrated while trying to do basic stuff like email, searches etc. This basically mean every bit of data generated my anyone is permanently stored and its just about time until it will be searched for any useful stuff in case there is a situation like this again which there always will be.

[–] tfowinder@beehaw.org 7 points 2 days ago

I agree with most people here, bank it. It's nothing if you factor in at least 2 emergencies over next 2 years.