小红书看到越来越多agent团队招人像是要大干一场。但我觉得,别搞agent
现在开始搞agent的像是没玩明白的,看别人都搞了,好像还搞得蛮好?然后自己也要搞
不然早就开始搞了
现在才开始,我觉得真没啥好搞的,接下来模型即agent,不需要重复造一些落后的轮子搞一些所谓xxx工程,因为本来就不懂,能提供什么特别的输入呢?无论抄袭还是跟随都走在后面,别人已经左脚踩右脚加速度越来越大,怎么追上呀
另外,agent也只是个跑在循环里的自动打字机而已呀,还有啥好搞的呢?anthropic都说要搞skills了当然要听他们的都是为了你好
Ralph的流行把这种简单真相摆在所有人眼前不能视而不见:
for ((i=1; i<=$1; i++)); do
result=$(docker sandbox run claude --permission-mode acceptEdits -p "@PRD.md @progress.txt \
1. Find the highest-priority task and implement it. \
2. Run your tests and type checks. \
3. Update the PRD with what was done. \
4. Append your progress to progress.txt. \
5. Commit your changes. \
ONLY WORK ON A SINGLE TASK. \
If the PRD is complete, output <promise>COMPLETE</promise>.")
if [[ "$result" == *"<promise>COMPLETE</promise>"* ]]; then
echo "PRD complete after $i iterations."
exit 0
fi
done
不过,我是agent的环境,还是得搞好环境