@DinariGlobal What's the point of buying shares via Dinari when the quoted price in your website differs significantly from the actual exchange price during normal stock trading hours π‘
@mtpelerin May I ask if I were to send fund to this IBAN personal account, in the wire transfer how can i proof to my bank this is my IBAN under my name? And if I were to transfer back to my bank account, how can I proof the source of fund is actually from my name?
@lydiahallie Your explanation doesn't make sense. So basically the message is: Users' fault! Right? Disable thinking, go to a lower quality model. The real solution without any investigation required from your end is to undo whatever changes you have make that causes this issue.
@MilksandMatcha To contribute towards better software. I would use it to build my new SaaS agency that helps small blue-collar companies use AI for managing their businesses and contribute to open source project.
@lydiahallie Only 2 to 3 prompt and I have reached my session limit. We should not be penalize when it was Claude Code which reach the tool limit and didn't complete its task. Worst, when it return with a fix, there is always a bug somewhere and we have to waste time to upload the log files.
@boxmining@kilocode@MiniMax_AI I have tried Minimax, it is no where near Claude performance in coding. Too bad they have removed the free tier, otherwise I will provide my valuable feedback for them to improve from my coding.
@trq212 It doesn't matter what time the usage is, I feel like it there is no difference as my dailly session max out after 2 to 3 prompts compared to last week before your changes. Please look into this more carefully, don't short change your customers.
MiniMax M2.7 scores worse than M2.5 on BridgeBench.
M2.5 ranked #12. Overall 92.3.
M2.7 ranked #19. Overall 88.1.
UI dropped from 76.6 to 61.9.
Refactor from 97.3 to 90.7. Gen from 94.3 to 89.2.
#1 on Multi-SWE Bench.
#19 on BridgeBench.
That's a 18 rank difference between synthetic benchmarks and real vibe coding evaluations.
This is why BridgeBench exists.
https://t.co/qJPpDM9pQQ
@trq212 I have been complaining about the Conversation compacting issue many times already but it is still not resolve. Upload more than 500 lines of code, compacting , then the AI will ask you to upload your code again because it cannot find anything in its filesystem.
@budapp Currently I am subscribe with Claude directly for the Pro plan. What is the difference if i subscribe to Claude vs Orchids where i choose the model Opus4.6? Do i get the same number of subscription tokens and usage? Which is betetr?
@claudeai@claudeai Before we apply, can you fix your existing Sonnet4.6 bug where any file uploaded more than 600 lines, it will auto compact the conversation and complain no file uploaded or found on its filesystem. Upload code file again, same auto compact conversation again.
@claudeai Sonnet 4.6βs 1M token context window? I keep getting please start a new conversation when i uploaded my code files the first time in a new char window.