GLM 5.2 in Amp. Zero data retention, US and West-based inference. It's a good model.
Try it now:
amp update
amp plugins add --auto-update @amp/glm-52-mode
amp --mode glm-5.2
@ClintFiore Why would we carry water bottles? We have water at home or in work. Your on your holidays, I carry my wallet, phone keys, why the fuck would I lug around a water bottle?
Opus 4.7, stopping 1 min into a task:
Wait! Which Option would you like?
A - This option is good and will solve your problem
B - This option is bad and won't fix anything
C - This option is just filling space
I would recommend Option A. What do you want to do?
@sqs I was in a thread working on feature, I got the "Update amp and continue thread" popup and clicked it, it I guess updated amp and run the continue thread command. But everything from that thread dissapeard. If I go to web view it says the thread is 10h old, but it's empty
@sqs@zxcodes@AmpCode I agree with OSS models changing all the time and being late to frontiers for couple of months, I mentioned them just because the pricing of the tokens lately has been crazy. But if byk stays in this form, money isn't going to be problem anymore, at least for me
@sqs@zxcodes@AmpCode First of all I've been testing OpenAI sub(plus) last couple of hrs and it's game changer tbh. I'm in early adopter/free tier zone, but I often top up(~50-100$/m). If this stay, I wouldn't even mind if you charge bigger fee for yourself tbh.
@sqs@zxcodes@AmpCode Nice, I'm looking forward testing it today. Also I personally wouldn't mind you exploring models like Kimi/GLM/Etc. and blessing them with you Harness, just as a cheaper option.