In general it's better asking questions after the content, and T=0.7 is way too high. Here's HN homepage summarized with T=0 and TopP=1, asking "Summarize the content above.":
DV2> The content above is a list of the top 30 stories on Hacker News as of 2 hours ago. Each story includes the number of points it has received, the number of comments, and a brief description.
DV3> The above content is a list of 30 posts from Hacker News, featuring topics such as new GPT-3 models, US Reps urging the DOJ to investigate anticompetitive conduct, intentionally making close friends, enabling the future of GitHub's REST API, curation and decentralization, making close friends, learning C, FFmpeg, open-source tabletop board game simulator, hiring engineers to unify ML, illegal hashes, designing Windows 95's user interface, a three-sided coin, high performance data integration framework in Go, Mauna Loa eruption, AirDrop being limited to 10 minutes, 26 lines of code that changed the world, SwiftUI being slow, AVX 512 being the future, a directory of Mac menu bar apps, the ATtiny 2-Series, a Fijian island being strangled by vines, hospice becoming a for-profit hustle, protecting from what one wants, a psychoactive substance, AI WordPress code snippet generator, open source and saying "no", a factory that only builds white Toyota Land Cruisers, widget.json and widget construction set, and lab-grown timber/wood.
I followed your advice and tried with Temperature 0.0 and rather than paste more walls of text I edited what I got. Sorry if that's bad form? I also upped the max tokens to 100 to better compare with the fb can model. Interestingly whilst the davinci 003 model changed output and was still subpar IMHO, the davinci 002 didn't change at all. I wonder if its cached internally.
If I am not mistaken, the temperature parameter controls the amount of randomness in the output. A temperature of 0 will always produce the same output. It is not caching as far as I know.
yes, T=0 means no randomness, and given sufficient tokens the output should always be the same (in such case whether they cache is a matter of hit ratio, I'd guess)
DV2> The content above is a list of the top 30 stories on Hacker News as of 2 hours ago. Each story includes the number of points it has received, the number of comments, and a brief description.
DV3> The above content is a list of 30 posts from Hacker News, featuring topics such as new GPT-3 models, US Reps urging the DOJ to investigate anticompetitive conduct, intentionally making close friends, enabling the future of GitHub's REST API, curation and decentralization, making close friends, learning C, FFmpeg, open-source tabletop board game simulator, hiring engineers to unify ML, illegal hashes, designing Windows 95's user interface, a three-sided coin, high performance data integration framework in Go, Mauna Loa eruption, AirDrop being limited to 10 minutes, 26 lines of code that changed the world, SwiftUI being slow, AVX 512 being the future, a directory of Mac menu bar apps, the ATtiny 2-Series, a Fijian island being strangled by vines, hospice becoming a for-profit hustle, protecting from what one wants, a psychoactive substance, AI WordPress code snippet generator, open source and saying "no", a factory that only builds white Toyota Land Cruisers, widget.json and widget construction set, and lab-grown timber/wood.