Was discussing with @Kevin Carrasco over on his post and decided to post so it helps others too! (Discussion: https://www.skool.com/cliefnotes/html-over-md-files?p=f349c1fc ), putting the core arguments here Recently, there was a twitter (X) thread that was talking about how HTML was the better choice over markdown and many claude engineers were making the switch. BUT, as experimented, HTML is over 2x costlier than markdown. I made a report with both md and html from the same content .md: 2k tokens html: 4.6k tokens (for the exact same information) More than 2x Thinking: .md: 3k - 2k = 1k html: 5.7k (direct gen from content) - 3.2k = 2.5k Again more than 2x Values are attached in the screenshots: 1. Generating md report from content (the one with 3k out tokens, 2k content and 1k thinking) 2. Generating html report from the same content (but this report had very little data so rejected this, still took more tokens) (5.7k out tokens, 3.2k content and 2.5k thinking) 3. Generating html report from md report instucting to put every piece of data (7k out tokens, 4.6k content and 2.4k thinking) The container tags have both open and close tags while markdown has just a single or a few character prefix for formatting. And then html has attributes, styles, all of which will require more tokens to represent. You can have more information in the same amount of tokens with markdown. There can be cases where HTML visualisation can cost lesser than a markdown one (ASCII art for drawing stuff. bar charts in ASCII is still cheaper.) and in those places you can just use html for those specific visualisations. Most markdown readers allow html rendering too for specific sections and you can have the rest of report in md. I have attached all output files too so you can see them. Markdown report is pretty nice too.

A Claude code Eng just dropped this. Anyone been doing this switch yet or will try? Curious to see what @Jake Van Clief has to say. It’s a file still just a different format. Same thing right… thoughts? Pros and cons? Here to learn and discover https://x.com/trq212/status/2052809885763747935?s=46&t=Ayzo8Ebbgb8PZhLNm057bg

You built your first folder. Vote below, then drop a screenshot in the comments so we can see what you came up with.

With the AMAZING support of you all in the last 24 hours upgrading to premium and VIP I decided to double down and drop some SERIOUS value for all of you for free as a giant thankyou and Proof I will work hard for you all. Yesterday Anthropic accidentally shipped the full source code for Claude Code inside an npm package. 512,000 lines of TypeScript. The entire CLI tool: every tool, every command, every system prompt, every unreleased feature flag. It was mirrored across GitHub within hours and Anthropic is now filing DMCA takedowns to pull it back. I spent the day going through it. Attached is a resource guide with every major repo, the best independent analysis posts, a table of the specific files worth reading, and a security warning you need to read before you touch any of it. Here is what matters for this community. ✨What it is: The source code for the Claude Code command line tool. The orchestration layer. How it manages conversations, picks tools, handles permissions, compresses context when the window fills up, and coordinates multiple agents working in parallel. This is production AI tooling at scale. ☄️What it is not: The Claude model. No weights, no training code, no API backend, no safety infrastructure. This is the client that talks to Claude, not Claude itself. If Claude Code is a car, we got the dashboard and transmission. Not the engine. 💯Why it matters for builders: 90% of this codebase is traditional software engineering. TypeScript, React, Zod validation, file I/O, error handling. The AI is maybe 10% by volume but most of the user-facing value. That ratio should sound familiar. It is the 60/30/10 in practice. The hard problems are not prompt engineering. They are context management, permission architecture, tool orchestration, and figuring out when to compress, when to truncate, and when to let the human decide. 🤫 Why I think it might be a marketing stunt: Every major feature that leaked (an always-on background agent called KAIROS, a tamagotchi pet system, 30-minute autonomous planning sessions, multi-agent coordinator mode) is now getting free press coverage across every tech outlet. These features are fully built and sitting behind compile flags. The "accident" required a specific change to the build config. And Anthropic was actively sending legal threats to protect this codebase ten days before it shipped to npm. Could be incompetence. Could be convenient. I will let you decide.

Tell us three things: 1. What you do (job, industry, student, career-changer, whatever) 2. What brought you to Clief Notes 3. One thing you're trying to figure out right now related to computing or AI I'll respond to every single one. And read each other's intros too because the person who's stuck on the same problem as you might already be in this thread. I'll go first I am Jake, I have been working in tech for 15 Years, building with Generative AI for 3 Years straight now! Excited to teach and learn! That's it. Simple, scannable, gives you data on who's joining and what they need, and keeps the feed clear for content that retains people past week one.