Mydtlwn
Mydtlwn
能否增加一个关于新冠变种信息查询的插件,关于信息源信息参考
https://github.com/cov-lineages/pango-designation https://github.com/cov-lineages/pango-designation/blob/master/pango_designation/alias_key.json https://github.com/cov-lineages/pango-designation/blob/master/lineage_notes.txt
There is also a small error that actually carries the S:R403K mutation, which is misspelled as S:K403R in the report.
确实如此,在一些极具灵活的问题上,星火大模型的回答还不如文心一言,比如让他改掉某一段,保留某一段,经常他就是将答案改了问题的题目,然后将答案原封不动的发一遍,幸亏我不是主管,他不是员工,否则他会被骂死,因为我不是敷衍的领导,让你改,而且给了修改意见,结果转了一圈,什么都没改。你觉得如果是现实中真的不会被炒吗?还有就是星火大模型值得吐槽的一点,给的方案很多都是排比句,但是现实当中的方案,可没有这种字数,格式完全对齐的情况,很多的人都会要求多变性,这种对齐的体验,在现实中的体验似乎是并不好,还有就是过于鱼的记忆的这种毛病,明明已经纠错了,然后当面它改了,然后你根本不需要太长时间,重新问它一遍,那个错误又会原封不动的出现。
我觉得应该增加一套错误复原测试,就是纠正错误后的,在短时间内重复一样的问题时的错误复原评分,如果这个错误经常无法纠正,那么就说明他的抗错能力差。不怕在其他方面出错,但是重复在一个错误上跌倒两次这是不允许的,特别是在短时间内重复出现一模一样的错误。
It should be added that the mutations of S:S31F, S:S31P, S:S31Del, and S:F59S seem to be convergent mutations, and there is also a sign of convergence in the mutation on...
I think it would be better to replace issues regularly every one to three months, with the expiration date and initiation date clearly marked in the title of each issue.
To distinguish from S:S31del, I suggest adjusting the combined name of S:F32del to De2FLiRT or De2FLuQE. If both mutations are present, they can be called 2DeFLiRT and 2DeFLuQE. Those with...
You're absolutely right, but this is just one possible scenario. Actually, I don't favor the simultaneous occurrence of both mutations either.