Steven Fortney
@steven-fortney.bsky.social
Applied Science @Uber. PhD in Financial Economics @Yale ‘21.
Okay yeah that’s actually exactly what I meant by contextual haha. Got it though. Cool stuff!
February 12, 2025 at 5:13 PM
Okay yeah that’s actually exactly what I meant by contextual haha. Got it though. Cool stuff!
Oh dang that’s a cool trick. Directly constraining the logprobs makes a lot of sense. I get how it works for a true/false binary (set all other tokens = 0) but any idea how it works for json? Is it a dynamic or contextual constraint?
February 12, 2025 at 4:30 PM
Oh dang that’s a cool trick. Directly constraining the logprobs makes a lot of sense. I get how it works for a true/false binary (set all other tokens = 0) but any idea how it works for json? Is it a dynamic or contextual constraint?
What do you mean by structured gen? Finetune on text/json input/output pairs?
February 12, 2025 at 2:43 PM
What do you mean by structured gen? Finetune on text/json input/output pairs?
True! I was more trying to point out that ranking on engagement gets you an (essentially) controversy-weighted “popularity” list.
For outbound clicks, choosing links from a whitelist of reputable sources can help the click bait problem but this is definitely not a complete solution.
For outbound clicks, choosing links from a whitelist of reputable sources can help the click bait problem but this is definitely not a complete solution.
November 28, 2024 at 8:15 AM
True! I was more trying to point out that ranking on engagement gets you an (essentially) controversy-weighted “popularity” list.
For outbound clicks, choosing links from a whitelist of reputable sources can help the click bait problem but this is definitely not a complete solution.
For outbound clicks, choosing links from a whitelist of reputable sources can help the click bait problem but this is definitely not a complete solution.
Absolutely. Part of the best thing about Twitter in the old days was that it felt like one of the few places you could see truly breaking news.
November 28, 2024 at 6:10 AM
Absolutely. Part of the best thing about Twitter in the old days was that it felt like one of the few places you could see truly breaking news.
measure of popularity than comment counts or even likes.
November 28, 2024 at 6:08 AM
measure of popularity than comment counts or even likes.
No concrete answers but I encourage you to think about the second-order effects of your algo. Eg if popularity is a function of engagement and engagement is a function of controversy then your algo at least partially rewards controversy.
More ‘silent’ measures (outbound clicks) might be a better
More ‘silent’ measures (outbound clicks) might be a better
November 28, 2024 at 6:05 AM
No concrete answers but I encourage you to think about the second-order effects of your algo. Eg if popularity is a function of engagement and engagement is a function of controversy then your algo at least partially rewards controversy.
More ‘silent’ measures (outbound clicks) might be a better
More ‘silent’ measures (outbound clicks) might be a better
Reposted by Steven Fortney
My idea for Econ seminars: speakers can go for as long as they want and talk about whatever they want. But we change the norm so that the audience can leave whenever they want and it’s nbd. Let supply and demand for attention determine seminar length/structure, etc.
November 21, 2024 at 2:04 AM
My idea for Econ seminars: speakers can go for as long as they want and talk about whatever they want. But we change the norm so that the audience can leave whenever they want and it’s nbd. Let supply and demand for attention determine seminar length/structure, etc.