注册并分享邀请链接,可获得视频播放与邀请奖励。

virushuo
@virushuo
Back to the 2006. Screeching voices of the minority. Author «Illustrated History of Programming»
2.8K 正在关注    63.4K 粉丝
在手机上tailscale+termux 连到家里linux电脑上 tmux + codex 这是我目前感觉最舒适的方式。依赖最短,网络可控,环境一致,想连多少台就多少台,想开vm就开vm。唯一的问题就是学习成本略高,但如果本来日常就是tmux+vim的组合,这个比任何app都舒服。不信你试试。
显示更多
感觉现在的IDE、Coding Agent客户端做了一堆,其实都无法代替tmux的工作区持久化、长时间任务不怕误关闭等功能。为什么Coding Agent不围绕tmux来构建人机交互呢?可能tmux的上手门槛还是高了一点点,主要是要记忆一堆快捷键。
显示更多
@virushuo designed by me (20 years ago) 我还从硬盘里翻出来了当年的官网设计
20年前,我的第一家startup是在为企业做搜索服务。20年后,现在我们还在做搜索引擎,只是从NLP换成了神经网络,从给人使用换成了给agent使用,但搜索仍然是重要的。开源我们的bm25,这是同等质量下,目前速度最快的bm25引擎:
显示更多
so we built psql_bm25s. exact BM25 retrieval. native Postgres access method. ~23x faster than pg_search on the standard benchmark. retrieval stops being a budget item. the harness stops rationing. the agent gets to look things up like it should have the whole time.
显示更多
0
1
140
19
转发到社区
Anthropic这个公司荒唐程度真的只有百度能与之相比了
THIS GUY LOST $200 IN ONE DAY BECAUSE THE STRING "HERMES.md" WAS IN HIS GIT COMMITS HERMES.md is a real convention used in AI agent projects. it's a system prompt specification file. not some obscure edge case he's on claude max 20x at $200 a month. yesterday claude code hit him with "you're out of extra usage" out of nowhere his dashboard showed 13% weekly usage. 0% current session. 86% of his plan was sitting there untouched but $200.98 in extra usage already burned through what should have been covered by his subscription he tried logout & login, different models, fresh installs and nothing worked anthropic support sent the ai bot (four rounds of the same scripted response). eventually they just gave up on him so he started binary searching repos and commits manually on his own time until he found the trigger the string "HERMES.md" in a recent git commit message uppercase, with the .md extension, anywhere in your commit history that's it claude code includes recent commits in its system prompt and something server side flags HERMES.md and quietly routes you off your max plan onto API rate billing > AGENTS.md? fine > README.md? fine > HERMES without .md? fine > lowercase hermes.md? fine > uppercase HERMES.md? you're getting charged API rates he reported it. anthropic support acknowledged the bug three times, called it an "authentication routing issue", thanked him for finding it then refused to refund the $200 so the man pays $200 a month for max, lost another $200 to a billing bug they confirmed, did anthropic's QA work for free on his weekend, and got a "thank you for your patience" in return check your commit history before claude code quietly drains your account too
显示更多
0
10
208
14
转发到社区
看完deepseek v4就理解前几天老黄在podcast上怎么那么生气
0
44
344
3
转发到社区
这几天读的最有趣的东西,包括里面的x讨论。然后我第一个感觉是这套逻辑非常适合 diffusion llm,因为它天生就是多路并行的。
各种coding plan都在涨价,不能推出token变贵了这个逻辑。对比 gemma4 31b和 gpt-5.0 两者智能水平接近,coding甚至gemma4更好。而gpt-5是10个月之前的sota。如今gemma4是免费且开放权重的,以10个月前标准看,token价格降低了不止90%。但是新一代模型更大了,也就更贵了。
显示更多
定期repomix一下丢给一个强ai用最强思考模式,会有奇效。
虽然不怎么看代码了,但我仍然会隔两天,离开终端,跑到IDE里面去看一下文件树。 这个东西很有意思,它看起来就是一些文件夹跟文件摆在那,但它们怎么组织,是否有矛盾冲突不合理的地方,一眼就能看得出来,把这个丢给AI,稍微聊两轮,你就可以接下来帮助他纠偏,帮AI把控一下方向。 当然,如果你不想自己看,你也可以让AI来看这个事情,就是在不看代码的情况下,只看代码文件是怎么摆的。 这个结构里面可是有非常多的信息的。
显示更多
一个中国人的名字里藏着他出生那一年的新闻联播。比如叫建国的,我们都能猜出他的年龄。 为了做 2000 万有机虚拟中国人的数据集,我花了几天让模型学会了名字和出生时代的关联。记录如下:👇
显示更多
0
11
87
14
转发到社区