All of these tests performed far better than what I expected given my prior poor experiences with agents. Did I gaslight myself by being an agent skeptic? How did a LLM sent to die finally solve my agent problems? Despite the holiday, X and Hacker News were abuzz with similar stories about the massive difference between Sonnet 4.5 and Opus 4.5, so something did change.
OpenAI Robotics head resigns after deal with Pentagon
bippy allows you to access and use react fibers outside of react components.。关于这个话题,新收录的资料提供了深入分析
经过几天高强度测试和对周边玩家的访谈,我还得出了以下观点:1、这东西的门槛不止安装,希望更高效的训练AI,基础代码技能、对AI底层技术理解能力还是要有的,但提示词的想法,创意,尤其是精炼或许更重要。2、Token成本确实不低,希望大厂们卷起来,不过相比海外已经很便宜了。3、确实有少数玩家能把小龙虾布置得服服帖帖,但是这群人是少数,并且每个行业都有这种少数人存在。4、正因为有门槛,所以消除门槛肯定是大厂们都要抢着做的事情,正如之前的计算机出现了操作系统一样,实现进一步的技术平权后,才是真正百花齐放的时候。5、现在看到的“高中生用小龙虾当老板”之类的,特别让你焦虑的文章,基本下面不是课程,就是卖产品,要么就付费社群。6、截至目前,小龙虾确实“越用越聪明了”,他和我都在进化,互相磨合,期待它未来的表现。7、焦虑要有,但需适可而止。
,详情可参考新收录的资料
I call them "hacky reimplementations" in the spirit of Emacs Solo:
Jetpack Compose,详情可参考新收录的资料