Vik Agarwal

@codevibesmatter @trq212 Reasoning traces are temporary, think of it like scratch paper vs a lab notebook. I actually maintain two sets of notes - One for decisions taken by Claude and one for Product Development Decisions taken by me.

@GeeksMirage @trq212 Then it would be much better to use reasoning traces for that

a prompt I've been using a lot recently: implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know

@codevibesmatter @trq212 You’re assuming that this is to track progress, which it is not. It is used to track historical decision flow, so that you have a log of WHY the LLM made decisions, so that you understand what happened and can improve it if needed in the future.

@trq212 Because you shouldn't have to track progress manually like this there's tons of inherent drift. Deterministic workflows with stages, modes, gates and verifiable outputs is the way

@trq212 For output only though, not input

HTML continues to be undefeated

@techNmak Link?

Andrej Karpathy wrote something that every Claude Code user has felt but couldn't articulate. Three quotes. Read them slowly. "The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should." "They really like to overcomplicate code and APIs, bloat abstractions, don't clean up dead code... implement a bloated construction over 1000 lines when 100 would do." "They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task." You've seen all three. Probably this week. Someone turned these three observations into a single CLAUDE[.]md file. Four principles, one install, directly addresses each quote: 1./ Think before coding Don't assume. Don't hide confusion. State ambiguity explicitly. Present multiple interpretations rather than silently picking one. Push back if a simpler approach exists. Stop and ask rather than guess. 2./ Simplicity first No features beyond what was asked. No abstractions for single-use code. No "flexibility" that wasn't requested. No error handling for impossible scenarios. The test: would a senior engineer say this is overcomplicated? If yes, rewrite it. 3./ Surgical changes Don't "improve" adjacent code. Don't refactor things that aren't broken. Match the existing style even if you'd do it differently. If you notice unrelated dead code, mention it, don't delete it. Every changed line should trace directly to the request. 4./ Goal-driven execution Transform "fix the bug" into "write a test that reproduces it, then make it pass." Transform "add validation" into "write tests for invalid inputs, then make them pass." Give it success criteria and watch it loop until done. This last one is Karpathy's key insight captured directly: "LLMs are exceptionally good at looping until they meet specific goals... Don't tell it what to do, give it success criteria and watch it go." It's a single file. Drop it into any project.

@trq212 HTML is great for Claude output and for further consumption. HTML from existing webpages is not great, a single long text website page can sometimes use the memory of a whole project!

@helloitsaustin @AnthropicAI Amazing stuff! Now this should become a live ticker, so that anyone can click on a date and see the “emoji of the day”. Much more accurate than Mood Rings 😂

I got married this past weekend so I did what any rational @AnthropicAI employee would do and had Claude Code analyze 12 years of iMessages with my wife, then Claude Design used that data to whip up a website for our guests in just minutes.

@MrBeast Super cool twist! When are you going to add the survivor coin and the Mrbeast survivor buff to the beast shop?!

Grew up watching Survivor, so getting to be a part of it tonight was a big moment to me. This show isn’t about celebrity, it’s about the stakes and the competition, which is why I tried to lay back and keep the focus on the competitors. I hope you all love it :)

@felixrieseberg Is this only for Claude code? Super sad, I’ve really needed this multi chat feature for Claude projects. Because when you start a query and switch chats, it stops executing. So I have to use Claude app, Claude web and Claude mobile to run 3 project queries :(

Some of the new features: An integrated terminal, in-app file editing, a rebuilt diff viewer, side chats, SSH connections - and a large amount of little quality of life. Download or update the Claude desktop app to get started: claude.com/download

Today is a big day! We're launching a ~ new ~ version of Claude Code in the desktop app. It's been redesigned from the ground up for parallel work and is a lot faster. It's been my main way to use Claude Code for the last few weeks.

@henrythe9ths How do you keep this data extra private and extra safe due to all the PII and sensitive nature of information?

Available to all users on desktop and web. Try it with Claude Cowork for best results. Connect now: claude.ai/directory

Tax season is here and a connector is all it takes to make @claudeai way more useful. Checkout what we just shipped: Connect TurboTax or Aiwyn Tax (formerly Column Tax) to Claude to estimate your refund, see what you may owe, and get a better understanding on the forms before you file.

@lennysan @rohang98 @AnthropicAI Yup, thats what I thought too. From Claude to Grok.

@rohang98 @AnthropicAI 🫣

Amol (Head of Growth at @AnthropicAI) just joined Twitter. Follow for free alpha. BTW, can you believe they hit $30B ARR before they even released Mythos?

@lennysan @cursor_ai @GoogleAI @NotionHQ @supabase @v0 @gumloop @Fin_ai The platform should send an email when an offer is going away or is added. Missed superhuman by 2 days :(

Breaking: Lenny's Newsletter subscribers will be getting a free year of @Cursor_ai, @GoogleAI Pro (w/ Gemini), @NotionHQ, @Supabase, @v0, @Gumloop, and @Fin_ai This is on top of the 25+ premium products that eligible subscribers already get free for a full year, including Lovable, n8n, Canva, Manus, Gamma, Granola, ElevenLabs, Factory, Devin, Linear, and Wispr Flow. It sounds too good to be true, but it's not. If you’re already a paid subscriber, just keep an eye on your inbox—we’ll email you as soon as these new products go live. Not a paid subscriber yet? Now would be a good time to become one so you don’t miss out: lennysnewsletter.com/subscribe An important note: Some products are available only to Insider-tier subscribers. In the new batch, Cursor, Google AI Pro, v0, and Supabase are just for Insiders. Insiders get exclusive deals, and priority access to all deals. And now is the best time to become an Insider: The Insider price will increase from $350 to $400 on April 14. If you’re already an Insider, you’ll keep your current price. If you want to lock in the current Insider price before the next wave goes live, upgrade before April 14: lennysnewsletter.com/subscribe?plan… Explore all the amazing existing product deals here: lennysproductpass.com A big thank you to all of our incredible partners for making this offer possible.

@bcherny @kieranklaassen @trq212 In a code command (and app settings) show top 10 token usage, split by recurring and size. Similar to how tools find recurring subscriptions and how other tools show largest emails or files. Also really need a token window % usage per appchat to avoid getting cut off randomly.

@kieranklaassen @trq212 Nice, glad we found it. Thinking through with the team how to make this self serve

Resolved!! @trq212 helped me out debug where the token usage came from and it was my fault 100% Script to find token usage gist.github.com/kieranklaassen… I had a recurring script that ran every 5 minutes that should not have run every 5. I hope we can make it easier to detect these within Claude and Claude Code soon too.

@bcherny Is it the same when you build for Mac terminals vs windows power shell?

There's a lot of tradeoffs when building for the terminal. Unlike web, mobile, and desktop, terminal have fairly restrictive instruction sets for rendering: ANSI escape codes. There's an ANSI code for "move cursor to (x, y)", another for "write 'foo'", etc. It feels a little like writing Assembly. Because there is no ANSI code for "move the cursor to (x, -y)" to repaint a row that is out of the viewport, we have to use the code for "clear the entire screen" -- aka, flickering.

Today we're excited to announce NO_FLICKER mode for Claude Code in the terminal It uses an experimental new renderer that we're excited about. The renderer is early and has tradeoffs, but already we've found that most internal users prefer it over the old renderer. It also supports mouse events (yes, in a terminal). Try it: CLAUDE_CODE_NO_FLICKER=1 claude

@WillowVoiceAI @madvortex_ @WisprFlow Why not add that to the comparison list? Thats the real competitor.

@madvortex_ @WisprFlow We're so accurate that it almost feels like someone is actually listening to you...

Introducing Atlas 1. Willow's new frontier speech-to-text model. It outperforms ElevenLabs, Deepgram, OpenAI, and more by a wide margin. Built on the first scalable, human-powered transcription infrastructure ever built for real-time dictation.

@trq212 I’m guessing this is because of the overlap between 3 key geos - UK, US-East and US-West? Why not pause the intensive jobs and use /loop to schedule them to run outside the window? Versus a hard stop?

We've landed a lot of efficiency wins to offset this, but ~7% of users will hit session limits they wouldn't have before, particularly for pro tiers. If you run token-intensive background jobs, shifting them to off-peak hours will stretch your session limits further.

To manage growing demand for Claude we're adjusting our 5 hour session limits for free/Pro/Max subs during peak hours. Your weekly limits remain unchanged. During weekdays between 5am–11am PT / 1pm–7pm GMT, you'll move through your 5-hour session limits faster than before.

@EricJorgenson @elonmusk Like Walter Isaacson, with a twist!

🚨📕 THE BOOK OF ELON IS NOW LIVE!!! 🎉🚀 This is the book we WISHED @elonmusk would write… “All of Elon's most useful ideas, in his own words.” Learn directly from the world’s greatest entrepreneur, like you’re sitting across from him at dinner. It took FIVE YEARS to make this for you. Because it's built from hundreds and hundreds of Elon's public appearances. I went through 3,000,000+ words to collect the most useful and timeless ideas. The final book is ~50,000 words. Every word is USEFUL. (This is what I do. My first book, The Almanack of Naval Ravikant, is one of the top 100 most highlighted books of all time on Kindle.) Then, I spent $50,000+ on editing and design so it looks and feels beautiful. Then… > Foreword by @naval. > Visuals by @jackbutcher. > Blurb from @mrbeast. > Published by @scribemediaco. > And yes, approval on this idea from Elon himself, thanks to @samteller. I went Maximum Effort to make this an all-timer. We got 10/10 on reviews from early readers, then worked on it for ANOTHER YEAR. Why so much effort? My mission is to create One Million Musks. For a generation to lift our gaze and build, so our grandchildren live in a world beyond our wildest dreams. I’m an independent author. I don’t get an advance. I risk my own time and money to make these books. Then we give away millions of them. Digital versions are free. I believe this book can benefit every human, and if you can’t pay five bucks for it, I want to personally gift it to you. Because I know it is useful. Useful how? You may be seeking purpose, a mission worthy of your life’s effort. You may have a clear purpose and seek the tools for success. You will find both in this book. Get the benefits of Elon’s entire life of hard-won lessons in a five-hour, easy read. (I checked, it’s a 5th-grade reading level.) You’ll feel personally mentored by the greatest entrepreneur in history. Click below to buy it now on Amazon, Audible, or directly from me. Amazon: amzn.to/47avSuh Audible: lnkd.in/gi_7HrFP Me: lnkd.in/gS2xWUWH If you’re not sure it’s worth $4.99 yet, just start reading the free version. PLEASE take 6 seconds to Like, Bookmark, and Repost. Even better: send this to your friends, team, or Group Chats! I guarantee this book will improve their lives. Spread the word! Every little thing helps. Your support spreads good ideas around the world, helping people and making the future better for everyone. Thank you! Forward. Together.

@Google @googlemaps But can it find me parking at my destination??

Today @GoogleMaps is getting its biggest upgrade in over a decade. By combining our Gemini models with a deep understanding of the world, Maps now unlocks entirely new possibilities for how you navigate and explore. Here’s what you need to know 🧵

@bcherny is this only for questions about the current execution? or can we start planning the next session / asking about other features?

btw

@measure_plan Reminds me of this classic game: youtu.be/w9qibcygSps?si…

i made a game where you play the piano IRL to survive against waves of monsters started as a weekend project and a demo video. people online seemed to want it, so i turned it into a full game it's the first time i publish a paid game, and so far it's sold 240 copies in the first month most players are coming from IG. there's a lot of piano teachers and people learning music who like the concept v1 only had 1 game mode, but now there's 5 ways to play: notes, chords, scales, perfect pitch, full song battle more to come on Midi Survivor. more minigames and maybe a steam release too :]

@MaliceDaFirenze After you’ve enjoyed galloping everywhere, are there any goals or quests?

We're making a game where you play a courier rider in 13th century Mongolia No combat, just you, the horse(s) you've tamed, bred and trained and the vast wilderness. Would you play this?