Comment by polski-g 2 days ago This is a bad model. Worse than Luna in every way; slower, dumber. 3 comments polski-g Reply pphysch 2 days ago OAI/Anthropic shareholder? Speed and intelligence are not "every way". Cost is essential. Hence the Pareto boundary illustrated in TFA. polski-g 1 day ago It literally cannot complete tasks that Luna can do easily. It doesn't matter how cheap it is. freakynit 1 day ago It actually can. I have been using it regularly for past 4 days. It is on sol-low level. I deliberately tested it on a moderately complex task. glm-5.3-flash one-shotted it correctly. Luna max couldn't achieve parity even after 3 total attempts.It was creating java bindings for this project: https://github.com/jeffhajewski/latticedbAnd here is the binding one-shotted by glm-5.3-flash: https://github.com/jeffhajewski/latticedb/pull/5
pphysch 2 days ago OAI/Anthropic shareholder? Speed and intelligence are not "every way". Cost is essential. Hence the Pareto boundary illustrated in TFA. polski-g 1 day ago It literally cannot complete tasks that Luna can do easily. It doesn't matter how cheap it is. freakynit 1 day ago It actually can. I have been using it regularly for past 4 days. It is on sol-low level. I deliberately tested it on a moderately complex task. glm-5.3-flash one-shotted it correctly. Luna max couldn't achieve parity even after 3 total attempts.It was creating java bindings for this project: https://github.com/jeffhajewski/latticedbAnd here is the binding one-shotted by glm-5.3-flash: https://github.com/jeffhajewski/latticedb/pull/5
polski-g 1 day ago It literally cannot complete tasks that Luna can do easily. It doesn't matter how cheap it is. freakynit 1 day ago It actually can. I have been using it regularly for past 4 days. It is on sol-low level. I deliberately tested it on a moderately complex task. glm-5.3-flash one-shotted it correctly. Luna max couldn't achieve parity even after 3 total attempts.It was creating java bindings for this project: https://github.com/jeffhajewski/latticedbAnd here is the binding one-shotted by glm-5.3-flash: https://github.com/jeffhajewski/latticedb/pull/5
freakynit 1 day ago It actually can. I have been using it regularly for past 4 days. It is on sol-low level. I deliberately tested it on a moderately complex task. glm-5.3-flash one-shotted it correctly. Luna max couldn't achieve parity even after 3 total attempts.It was creating java bindings for this project: https://github.com/jeffhajewski/latticedbAnd here is the binding one-shotted by glm-5.3-flash: https://github.com/jeffhajewski/latticedb/pull/5
OAI/Anthropic shareholder? Speed and intelligence are not "every way". Cost is essential. Hence the Pareto boundary illustrated in TFA.
It literally cannot complete tasks that Luna can do easily. It doesn't matter how cheap it is.
It actually can. I have been using it regularly for past 4 days. It is on sol-low level. I deliberately tested it on a moderately complex task. glm-5.3-flash one-shotted it correctly. Luna max couldn't achieve parity even after 3 total attempts.
It was creating java bindings for this project: https://github.com/jeffhajewski/latticedb
And here is the binding one-shotted by glm-5.3-flash: https://github.com/jeffhajewski/latticedb/pull/5