zlacker

[parent] [thread] 7 comments
1. plufz+(OP)[view] [source] 2025-12-04 23:20:28
I know very little about how the environment where they run these models look, but surely they have access to different tools like vector embeddings with more current data on various topics?
replies(2): >>discon+t4 >>endtim+K5
2. discon+t4[view] [source] 2025-12-04 23:44:53
>>plufz+(OP)
you can (via the api, or to a lesser degree through the setting in the web client) determine what tools if any a model can use
replies(2): >>discon+j6 >>plufz+YQ
3. endtim+K5[view] [source] 2025-12-04 23:52:09
>>plufz+(OP)
If they could "see" the future and exploit that they'd probably have much higher returns.
replies(2): >>alchem+79 >>plufz+LQ
◧◩
4. discon+j6[view] [source] [discussion] 2025-12-04 23:55:25
>>discon+t4
with the exception that it doesn't seem possible to fully disable this for grok 4
replies(1): >>alchem+99
◧◩
5. alchem+79[view] [source] [discussion] 2025-12-05 00:16:00
>>endtim+K5
56% over 8 months with the constraints provided are pretty good results for Grok.
◧◩◪
6. alchem+99[view] [source] [discussion] 2025-12-05 00:16:24
>>discon+j6
which is curiously the best model …
◧◩
7. plufz+LQ[view] [source] [discussion] 2025-12-05 08:06:15
>>endtim+K5
I would say that if these models independently could create such high returns all these companies would shut down the external access to the models and just have their own money making machine. :)
◧◩
8. plufz+YQ[view] [source] [discussion] 2025-12-05 08:08:23
>>discon+t4
But isn’t that more which MCP:s you can configure it to use? Do we have any idea which secret sauce stuff they have? Surely it’s not just a raw model that they are executing?
[go to top]