QIN2DIM

The default is to use the RESNET-50 model, which is behind the times in terms of inference performance. I will write a script later to determine if current hardware resources...

https://github.com/QIN2DIM/hcaptcha-challenger/blob/d5fa70a2c972293310e762761e9a168015f1185c/hcaptcha_challenger/onnx/modelhub.py#L295-L308

> I think we should work on a CI that converts collected information into CLIP candidates automatically so we don't have to keep track of them manualy. You're right. That's...

https://github.com/QIN2DIM/hcaptcha-challenger/blob/d5fa70a2c972293310e762761e9a168015f1185c/src/objects.yaml#L6 https://github.com/QIN2DIM/hcaptcha-challenger/blob/d5fa70a2c972293310e762761e9a168015f1185c/src/objects.yaml#L736

Updated Actually, I rewrote clip_candidates about two weeks ago and also solved the current issue. However, that feature needs more testing, and I have been too busy recently.

@Pocker88 sure, But I don't have enough data sets right now. Can you provide a stable sitekey for the forest?

By the way, this sitekey is very interesting and it allows me to be exposed to more types of challenges.

Maybe next time you find a new challenge you could provide the `getcaptcha/` packet information and a demo recording of the interaction. That way I can get the skeleton of...

去年年底开始盲测对比不同的 Agent 项目，三四个月过去了， MetaGPT 的稳定性还是只能用“千疮百孔”来形容，但总体上 idea 不错，需要努努力👍

IN PROGRESS🤖(/▽＼)