Allbirds, the shoe brand, now says it's an AI compute company.

we show that iterative self-refinement with LLMs, no matter the prompt, usually makes things worse. the model hallucinates flaws to satisfy critique prompts, each pass expands scope unchecked, and models almost never decline to make changes even when they should Autoreason fixes this by structuring each iteration as a three-way tournament: the unchanged original (A), an adversarial revision (B), and a synthesis of the two (AB), judged by a blind panel of fresh agents via Borda count. if A (ie "do nothing") survives two consecutive rounds, the loop stops

年齢を言い訳にしている全ての人へ。

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.

2月だけで 韓国の50人に1人が日本に来てるし 台湾の30人に1人が日本に来てるし 香港も30人に1人が日本に来てる。 2月だけだよ！2月だけ！！ 台湾と香港は1年で3人に1人以上の人間が日本に来てることになるぞwww

物欲を抑えたいのに田中シェンさんの着画を見てしまいArc'teryxをディグる手が止まりません..。魔力ある。まじで

I'm a realist when it comes to AI and thought I was aware of the scale of negative perception outside our bubble. I wasn't close. On a trip rn I'm getting an opportunity to talk to a variety of people and the sheer amount of "normies" who have negative views on AI is insane

Japanese men buy monster hunter the same way American men buy Madden I keep meeting dudes who aren’t into video games but they still got a ps5 with monhun

ピーター・ティール・パランティア・テクノロジーズ社会長@peterthielを官邸にお迎えし、日米の先端技術分野の現状及び展望等について、有意義な意見交換を行いました。 続いて、ＵＡＥのジャーベル特使の表敬を受けました。イランをめぐる情勢を踏まえ、ＵＡＥにおける被害にお見舞いを申し上げ、邦人保護や石油の安定供給を要請しました。また今回、日本・ＵＡＥの『包括的経済連携協定』が交渉妥結に至りました。この機会を捉え、様々な分野での協力を一層強化していきます。 その後、ドイツのメルツ首相 @bundeskanzler と先週以来２度目の電話会談を行い、メルツ首相から最近の訪中と訪米について説明をいただきました。また、世界のサプライチェーンに影響を及ぼす経済安全保障の問題について、日独両国が引き続き緊密に連携していくことを確認しました。

Japanese Prime Minister Takaichi met with Palantir President Peter Thiel in Tokyo today. This TV news report states that he is called "America’s Shadow President." Details of their meeting were not released to the public.

Ready to make the switch? claude.com/import-memory