
Ry
23 posts

Ry
@RR_ruby_y
只进行对等交流。逻辑掉线、只会复读情绪话术者,大脑尚未发育完全者,会自动触发单向屏蔽程序。Equal exchange only. Illogical takes / emotional parrots / underbaked brains = blocked.
kyoto Katılım Mart 2026
112 Takip Edilen13 Takipçiler
Ry retweetledi

总结一下AI投资最强00后 @leopoldasch 大佬的观点:
1. 普通人洗洗睡吧,快的话明年,最晚十年内,就都失业了
2. AI基建还有很多钱可以赚,市场大到超乎想象
3.美国的AI技术,很容易就被中国偷,这目前没啥好办法
4.美国要拿出当当年曼哈顿计划造原子弹的决心,all in AI
皇国兴废,在此一战!
大漂亮| C Labs@giantcutie666
中文

@RainbowXiaoMiao 这女的纯特么傻吊一个,这个小男孩才是真自信,仔细看着这女的表情,尤其是语无伦次那会,她意识到被人反向拿捏,内心有种挫败感和不自信油然而生,真自信且认知高的女人看到这个男生会是什么反应?
中文
Ry retweetledi

这世界不仅是个巨大的草台班子,还是个巨大的虚拟世界。我们现在就是在重播一战后到二战前的剧本,不信自己看。
1920s-1939:
> 美国右派总统Harding上台,喊”America First”(对,这口号比Trump早100年)
> 大萧条把中产一夜打成无产
> 年轻人往左冲,德国共产党冲到国会第三大党
> 右翼靠”反共产党”收割恐慌上台,一批最恨资本主义的左翼工人,转头投了纳粹
> 纳粹支持率4年从2.6%冲到37%,翻了14倍
> 西班牙内战变成大型代理战预告片
> 国联装死
> 1939,二战爆发,后面跟着几千万条命
2020-2026:
> Trump把America First翻出来
> 疫情+通胀+房价干碎中产安全感
> 年轻人又开始觉得“社会主义”挺酷。按 2025 年一项美国民调,18到29岁里,62% 对社会主义有好感,34% 对共产主义有好感。
> 右翼靠反woke反全球化反移民重新集结
> 一部分原本在左翼话语里的人,又开始往右翼极端漂
> 代理战遍地:俄乌、中东、霍尔木兹
> 美伊谈了21小时没deal,Vance上飞机走了
> 联合国装死
> ???
地球online这游戏连台词都不打算改了吗
上一次这套东西跑了快二十年。那会儿消息靠报纸,动员靠广播,武器是坦克。
现在消息实时,情绪算法喂,武器高超音速,历史在倍速播放。
1937年的柏林人,白天也一样正常上班。
Pickle Cat@0xPickleCati
@worldlibertyfi @justinsuntron 拿官号直接开大啊,这几天咋全世界都在玩过家家呢??🤣 CZ VS 徐明星,WLFI VS 孙割,美国 VS 伊朗
中文

蹲后续
WLFI@worldlibertyfi
Does anyone still believe @justinsuntron ? Justin’s favorite move is playing the victim while making baseless allegations to cover up his own misconduct. Same playbook, different target. WLFI isn't the first. We have the contracts. We have the evidence. We have the truth. See you in court pal.
中文

Numb to it. This is the way.
Peter Mallouk@PeterMallouk
Always something, yet the market finds a way...
English

@diqitianmowang @kennys548534 @ogden_walpole @HatagaleNayan 他好像低智儿童,一直揪着别人说是女的,别人是男是女都不影响别人爆料,他死皮赖脸、蠢得要死,只会让越来越多人爆他的料。早点道歉销号早就没什么事了,一直死鸭子嘴硬。
中文

@kennys548534 @ogden_walpole x的聊天信息是跟随账号的,也就是换一台新设备登录账号都能看到之前的所有的聊天信息。你在卖号以前是把聊天记录都删了吗?如果没有,那些私信你的人,她们的信息就可能被曝光。放着最安全的销户不做选择卖号,跑路还想再赚笔钱,这是人渣不是高端精英。刘磊,广州侨鑫集团员工@HatagaleNayan认领一下

中文

网黄(或任何领域的kol)与普通网友之间,存在一种单向度的信息展示与群体崇拜结构。网黄展示的是精心剪辑的、符合受众幻想的“切片”,而网友则容易将自己的想象投射进去。这种关系从一开始就不是平等的双向看见。
Ry@RR_ruby_y
说来说去最好还是不要随便约炮,就是要约也是对一个人有充分的了解和后续的考虑,而不是对互联网上一个有光环、滤镜的男性充满幻想就这样稀里糊涂地开始了,而且事实上这样一个在互联网上有光环的男性在某种程度上也是权力关系的上位者。
中文
Ry retweetledi

LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
English









