Check my new article about Intermittent Casting. open.substack.com/pub/overcl…

I started my Substack. Check my first article: My brain was 21 when it shut down. open.substack.com/pub/overcl…

I can draw an #nft pfp collection for your project better and cheaper than others.

Join typing #WorldCup predictions with free entry on @JupiterExchange using my reflink: jup.ag/prediction/world-cup?…

I'm officially a Trencher now 🔥 just locked in early access to @TrenchersAI Let's run it up together! join the trenches → trenchers.ai/b1p70i50 #TrenchersAI x.com/TrenchersAI/status/204…

I miss the days when AI stood for Adobe Illustrator.

pulled Oracle on my @nodiens Intelligence Card. i read it early anyway. @nodiens access just makes it sharper. got mine here → access.nodiens.com/share/web…

Meanwhile, Poland’s largest opposition party, which formed the government during the previous term, today introduced a bill that would ban crypto related companies. 🤡

If you vibe coding and thinking about your own web3 startup - NFT project is the fastest way to: - build a community around your product, - raise initial funds for development, - validate your narrative before MVP. If you’re interested in premium 2D art -> get in touch. 🤜🤛

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.

Opublikowałem raport o wpływie AI na polską gospodarkę i finanse publiczne. 65% budżetu państwa opiera się na pracy ludzi, a AI tę pracę zaczyna zastępować. Oddolna inicjatywa, zero zleceniodawców, za darmo. agipoland.eu

Przez lata spieraliśmy się: euroentuzjaści kontra eurorealiści. Obie strony się myliły. 18 maja, na konferencji w Brukseli, po raz pierwszy publicznie przedstawiłem koncepcję EWG 2.0. Reakcje utwierdziły mnie w przekonaniu, że czas najwyższy powiedzieć to głośno i wprost.Cieszy mnie to że coraz więcej głosów w przestrzeni publicznej potwierdza, iż jest to dobry pomysł! Europa, która zaczynała jako projekt prostoty i wolnego rynku, zamieniła się w maszynę do produkcji regulacji. Europejski motyl, zamiast rozwijać skrzydła, owija się w kokon procedur i absurdów. Czy da się to odwrócić? W moim felietonie dla @xyz_oficjalnie rozwijam tę ideę i proponuję konkretną odpowiedź, czyli siedem zasad, które mogą przywrócić Europie to, co kiedyś czyniło ją potęgą: odwagę, konkurencyjność i wolność gospodarczą. Piszę też, dlaczego Polska powinna stanąć na czele tej zmiany i dlaczego tym razem musimy działać ponad podziałami. Bo jeśli Europa nie odzyska skrzydeł, inni napiszą jej przyszłość za nią, a tym samym będziemy tego ofiarą,a nie beneficjentem. 🔗 Link do artykułu: xyz.pl/rafal-brzoska-ewg-2-0…

🔴Kto jest tak naprawdę beneficjentem SAFE? - tłumaczy mec. Jerzy Kwaśniewski⚠️

Folks x @SPACEID SPACE ID domains are now supported on Folks Finance. See your portable Web3 identity instead of raw wallet addresses across chains while lending & borrowing on xChain.

SPACE ID domains are live on Folks Finance. To celebrate, we’re giving away 100 $USDC 🎁 1️⃣ Like & Repost the announcement below 2️⃣ Tag frens 3️⃣ Follow @FolksFinance & @SPACEID Winner announced in 48h.

"Jakie warunki musieliby spełniać ci ludzie, abym uznał ich za elity zdolne sprostać wyzwaniom stojącym przed Polską? Muszą mieć silne poczucie własnej wartości oraz być głęboko zakorzenieni w Polsce – w jej terytorium" - mówi Jacek Dukaj. 👉Jakich elit potrzebuje Polska? Zapraszam na debatę z @pio_tru oraz @mluczewski z @ForumKrynica. Link w komentarzu.

In partnership with our friends at Lucid, we’re giving away 5x $1,000 in $LUCID at their TGE! To enter: 1) Follow @OkayBears and @LucidChain 2) Like, RT, and nominate 2 people in the comments. 🏆 Winners announced Monday.