Hasen 🦭/acc
5.5K posts
@ClaudeDevs This web version of claude code is genuinely the worst, took 15 mins to da a task as it went into thinking consumes limits crazy and if runs out of tokens it forgets context completely. Better to remove
English
We’ve refreshed Claude Code on the web and mobile. A few things that recently shipped 🧵
English
@WazzCrypto @AIandDesign Teach me bro, I'm building app- total 7k lines and even today as limit reset I'm already 43% of my weekly limit already. Should I do /compact often? Ex: ask 10 questions claude tries fixing them token runs out half way - should i /compact before saying continue?
English
@AIandDesign I run Opus on xhigh full time on like 7 diff projects simoustaneously and ive yet to hit any limit ever.
A pattern i've seen with ppl facing this is that they unnecessarily bloat its context and run lots of useless agents and skills
English
People who constantly run out of Claude tokens:
WTF are you doing?
I have a whole portfolio full of work made with it and I never run out of tokens.
Melvyn • Builder@melvynx
We can all say it... Claude 20x is dead. The previous "feel unlimited usage" doesn't exist anymore. Usage increases quickly and scales really fast... People who discover Claude Code now: you missed a time that will never come back, I think.
English
Introducing Swiggy Builders Club
We’re opening @Swiggy commerce infrastructure to developers and enterprises to build on top - build AI agents, apps, and integrations on top of Swiggy’s Food, Instamart, and Dineout ecosystems - with real APIs, real data, and real users.
What you get:
3 MCP Servers (Food, Instamart, Dineout)
18+ API tools covering the full convenience stack
Production data access from day one
Direct engineering support
Who it’s for:
Individual developers with bold ideas
Startups building AI-native commerce products
Enterprises looking to integrate Swiggy into their platforms
Smart grocery restock bots. AI ordering assistants. Dining recommendation agents. Group ordering tools, health first products.
If it makes commerce better for users, we want to see it.
Ship something great and we’ll feature it. Ship something exceptional and our recruiting team might reach out.
English
I've created a full guide on how to design anything with Claude Design
You also get exact copy-paste prompts for interactive immersive websites, animated pitch decks, app mockups, social banners, infographics, and pricing pages
Grab it FREE
Like + Comment "CLAUDE DESIGN" and I'll DM you the full guide
No opt-in, no BS
English
@bcherny @HackingDave It lies a lot and says it did things when in reality it doesnt really have those executed
English
👋 Is there a specific issue you're hitting? If so, would you mind running /feedback and sharing the id here? That would be most helpful for debugging.
There were a number of harness changes that may have caused this, all of which are fixed in the latest (last known issue was fixed in 2.1.116 today). We will be sharing more in a bit, and have also shared a few updated on X/Threads as we've been investigating.
General tips:
1. Use Opus 4.7 + xhigh/max effort
2. Make sure you're using the latest version of Claude Code (currently 2.1.116)
English
For the enterprises using Claude, if you are using it for heavy enterprise type stuff - be extremely careful. It's introducing massive bugs, security issues, and code quality is way worse than Opus 4.5, substantially worse on both 4.6 and 4.7.
Our entire development team is shifting off of it. It's unusable at the moment aside from beautiful UI stuff, it's code quality is not something you can trust.
Still no word from Claude on why they mangled their models and didn't tell anyone - which is particularly alarming on every front.
I would recommend switching teams over to something like Cursor, Perplexity, or AWS Bedrock - as the frontier models continue to innovate (or regress) - having the ability for flexible model selection that doesn't disrupt development workflow will be insanely important for enterprise.
English
@CoreyWriting Why are yall talking about this like its a new
discovery. There are multiple studies and philosophical thoughts around this concept. Fuckin duh.
English
The looksmaxxers are correct that humans see physical attractiveness as an indicator of moral virtue in and of itself. If society is shallow, and you're rewarded based on appearance, then the incentive structure is set up to embrace this truth by caring a lot about your looks.
🐰@c_tviz
this tiktok comment could not be more true
English
@amorriscode @bruvimtired @claudeai @AnthropicAI Why does claude switch between max effort and reduced context window automatically in chats? Yesterday i was working with high cobtext it used to name me by my name and today it was the user says and i don't have enough context. What is actually going on?
English
@bruvimtired @claudeai @AnthropicAI 💀 400 is a backend issue obviously. sorry that your first try was scuffed.
English
Claude Code leak got everyone building agents- I made one that actually runs on mobile!
Meet Claw-Termux (Clawt): native Termux agentic CLI assistant. Zero bun/Rust/dependency hell. Full tools (bash exec, file ops, grep+).. GitHub...Proof it works on Android attached #claudecode
English
Hasen 🦭/acc retweetledi
@mikeyk Weekly limits were exhausted but the new bonus doesn't seem to be in place
English
We’ve doubled usage on weekends, and outside 5a–11am PT on weekdays, through March 27.
Works across Claude.ai, Cowork, and Claude Code. Go run your next big idea and thanks for building with us!
Claude@claudeai
A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.
English
@bcherny It doesn't seem to have applicable for those that hit their weekly limits already, could you look into that
English
We doubled Claude usage on weekends, and outside 5–11am PT on weekdays for the next 2 weeks.
Claude@claudeai
A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.
English
@trq212 Still at 0 for me, doesn't look like the changes were applied
English
@lyemningthou Why can't we join, keeps saying failed to send, pls try
English
100%. Humanoids will need orders of magnitude more real-world behavioral data than people realize, especially outside tightly controlled environment.
TBPN@tbpn
Training humanoid robots on teleoperation alone won’t scale, says Rhoda AI CEO @startupjag. Unlike self-driving cars - which basically have four actuators (left, right, speed up, and slow down) and operate in a single environment (the road) - humanoid robots are completely different: "You're dealing with the full dexterity of a human hand - 20 degrees of freedom per hand. Every object is different. Every type of task is different." The problem isn't just the quantity of data - the bigger issue is diversity in the data, and it's why many humanoid robot demos will struggle to adapt to the real world: "If all the data you have is data that you've intentionally collected, then you almost by definition haven't seen the corner cases. You haven't seen all those edge scenarios that cause failure." Jagdeep says teleoperation is useful for fine-tuning robot behavior, but for pretraining, it's completely inadequate.
English
@lyemningthou Is the site down because I'm unable to register! How do you guys ship to India btw?
English
In the United States, India, Nigeria, and the Philippines, over 1,000 restaurants, hotels, and households use Asimov to turn their daily routine into a living.
Learn more and join us at tryasimov.ai.
English
We're excited to announce Asimov (YC W26), we're building the data infrastructure for the GPT-3 moment in humanoid robotics.
We provide the largest robotics labs with thousands of hours of that data every day, and empower households and businesses worldwide to earn a living by recording what they already do.
Y Combinator@ycombinator
Asimov (@tryasimov) pays households and businesses worldwide to record their daily routines, generating thousands of hours a day of diverse human movement data to train humanoid robots. They've built a global network, along with the full stack, from proprietary collection hardware to annotation tooling, and are already providing data to the largest robotics companies in the world. Congrats on the launch, @lyemningthou and Anshul! ycombinator.com/launches/PeH-a…
English
Hasen 🦭/acc retweetledi
The future of warfare is autonomous. If you’re not invested in drones, anti-drone defense or drone components wtf are you even doing?
Naval@naval
Drones are easy to make, hard to stop, and bring Mutually Assured Destruction to conventional warfare.
English