Sam Elrad

Anthropic just automated the first-year analyst job at every bank on Wall Street. They released these 10 AI agents for finance: → Pitch builder → Meeting preparer → Earnings reviewer → Model builder → Market researcher → Valuation reviewer → GL reconciler → Month-end closer → Statement auditor → KYC screener The analyst pyramid just got a lot flatter.

This is the the quote I've been citing a lot recently.

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

This is one of the most important weeks of your life It is more than likely both Opus 4.7 and ChatGPT 5.5 will release in the next few days Both will be humanity shifting technologies When massive shifts drop like this you need to do EVERYTHING in your power to be using them the moment they come out You need to be calling in sick from work You need to be asking your significant others to watch the kids You need to be faking your death so your friends don't call you You do what it takes to get your hands on these pieces of technology When we have nuclear shifts in the landscape, massive opportunities arise. This will be one of those times There's going to be a short time period after the release of these models where it will be easier and faster than ever to build revolutionary products, and not many people will be doing it If you jump on these opportunities, you can build life changing wealth. These are the times where people put on the AI sorting hat and that hat says either "permanent underclass" or "permanent overclass" Take these actions now: • Download Claude Code Desktop • Download Codex app • Get your OpenClaw ready for the update • Learn these tools inside and out • Moment the new models drop plug them in and use them Your entire lineage is depending on this

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.

You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.

Sam Altman predicted the first one-person billion-dollar company. Matthew Gallagher built a $401M company in year one with $20,000, AI tools, and zero employees. This year he's on track for $1.8B. With 2 people. The playbook has changed: Old path: - Come up with an idea - Fundraise from friends or VCs - Hire a team - Build the product - Hope it works New path: - Start with an audience (X, Instagram, TikTok) - Vibe code something for that audience - Build a community around it - Automate fulfillment with AI agents - Repeat That's the new barrier to entry is a laptop and an idea.