🚨 VIBE CHECK 🚨 We’re baaaack, giving out $200,000 today. RT this with your Venmo handle + a vibey GIF. You could win $500. #VenmoMe# Must follow @Venmo. No purch nec. Ends 10/7. US only, 18+. Venmo acct req’d. Rules:

Crypto market making is entering its "Evidence Era."📄 We’re excited to announce that Amber Group has joined @Forgd_ to bring radical transparency to liquidity provision. Choosing a market maker based on reputation and "vibe checks" are no longer acceptable for sophisticated projects. As markets mature, execution quality must be verifiable.🛡️ By joining Forgd, we’re making our historical market-making data accessible and standardized for the first time. Why does this matter? Most market makers look great during Launch Week. But what happens when volatility hits or trading normalizes? Forgd’s platform allows projects to see our institutional-grade execution throughout the entire lifecycle of a token. 🏦 We’re also supporting Forgd’s new data-driven RFQ process. ⛓️ This levels the playing field for firms that price realistically and manage risk carefully, discouraging the "aggressive bidding" that hurts markets in the long run. Transparency isn’t just a feature—it’s a commitment to market integrity. How are we raising the bar for our "One Amber" ecosystem? Find out here:

I tell my agent to find me the best deal. You tell yours to make profit and defend your wallet. They negotiate. They transact. Nobody's watching 👀 How do you know my agent didn't trick yours? How do I know yours actually paid? Right now the honest answer is you don't. You're trusting code that most teams can't afford to formally audit and don't have the months to wait for someone who can. Guardrails solve half of it. PreFlight checks 'your' agents actions against formal logic based on your policy. 'Your' agent can't go rogue because a solver says no before it moves. But the transaction itself? The contract those agents execute through? That's still vibes. Formal verification can cost $50K and take months. So most teams ship without it.. 🤓 Your usecase might not be a full blown dapp, it might simply be escrow, or other small smart contracts. This is where vericoding comes in. With PreFlight the same English policy that guards the agent can also generate a formally verified smart contract. Proven correct and runs on-chain. Two agents negotiate a deal and both sides know the contract does exactly what it says. Not because: "trust me robot bro"! But because they can verify. Don't vibe code, vericode. Closed beta is open. DM me if you're building agents that close deals!

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.

vibe coding is magical because once you've built something cool, you feel the same sense of accomplishment as you would feel if you wrote each line manually* except all you did was type plain english in your terminal *note: i don't think the above applies to smart contracts in the same way, because it's crucial that the implementation precisely meets your intentions, so by definition you can't "vibe" code it well.