any
756 posts
Expo Agent now has templates for building full SwiftUI, and Jetpack Compose apps right from the browser with just a prompt. No Xcode or Android Studio required.
Support is experimental. Join the waitlist today.
agent.expo.dev
English
@eastdakota @Cloudflare gg whole world wide web going down tomorrow i guess
English
Tomorrow is April 1. Many tech companies will do silly things. @Cloudflare has always taken the date as an opportunity to do things differently. #staytuned
English
@theo I generated this within 5 prompts using GPT-5.4 in Github Copilot with Skills.
Never in my life though I would be generating something like this by myself on a weekend.
English
GPT-5.4 is an incredible model for coding.
It’s a generation behind on fronted design.
OpenAI is suddenly acting like this is a skill issue. Don’t let them gaslight you.
English
English
Parseltongue has the best auto-decoder 🔥
Over 90 encoding methods auto-detected including:
Hex, Base64, Invisible Unicode, etc
I use this for everything now
Thank you @elder_plinius & @Ph1R3574R73r for the latest updates 🙏
English
agent-browser v0.21
It just keeps getting better (bc of you)
😮 `batch` command
😮 `network har` commands
😮 `upgrade` command
😮 iframe support
😮 --user-data-dir support
After this, you can just upgrade it:
npm i -g agent-browser
brew install agent-browser
English
Here’s a piece of alpha
An agent doing auto research
within an agentic loop
Vs
GSPO/GRPO And using final loss as a verifiable reward
Is the difference
between ICL and gradient descent
Karpathy assumes
ICL > Grad Descent
Which is False
English
In the next version of Bun
`Bun.WebView` programmatically controls a headless web browser in Bun
English
@Shpigford @claudeai its slower yeah but i wonder why is it still using explore agents when it can just read all the code at once?
English
sanity check: @claudeai's 1M context vs of Opus is slower than the non-1M, right? RIGHT?!?!?!
English
@yenkel @0xblacklight @dexhorthy Thank you. Going to send this blog post to claude to generate a CLAUDE.md
English
don't be lazy: write your claude.md by hand. yes, no AI!
highest leverage doc in your repo, so spend time on it!
more on what a good claude.md file looks like: humanlayer.dev/blog/writing-a… by @0xblacklight & @dexhorthy
English
@advaith I believe there isn’t, and that’s the strategy. Very clear to any power user though cause they can feel it in real time
x.com/pranit/status/…
Pranit@Pranit
Here’s what should bother you even more: Check Claude’s pricing page. API pricing? Crystal clear. $5/MTok input, $25/MTok output. Consumer plan pricing? “More usage.” “5/20x more usage.” More than what? They never say. It’d be trivially easy to put “X tokens per month” on that page. They do it for the API. They choose not to for subscriptions. That’s not an oversight. That’s a strategy. Undefined limits = unlimited flexibility to quietly adjust the ceiling downward. And you’d never know because there was never a number to compare against. You can’t accuse someone of moving the goalposts when they never told you where the goalposts were. That’s the whole point.
English
Anthropic just pulled the oldest trick in SaaS pricing.
I pay $200/mo for Claude Max. My limits have been noticeably worse this past week.
Now they announce 2x off-peak usage for two weeks. Sounds generous.
But here’s what actually happens: limits quietly drop, a temporary 2x makes the reduced limit feel normal, the promo ends, and you’re left at a baseline lower than where you started. You just didn’t notice the downgrade because the 2x absorbed the transition.
These AI plans are massively subsidized. The raw compute behind a heavy user costs multiples of the subscription price. Every move like this is the subsidy quietly correcting.
Very sneaky, Anthropic.
Claude@claudeai
A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.
English
Each time we deal with Apple reject, it takes like weeks, even with appeal form submitted.
I am really longing for future where we won't have AppStore reviews, you can install tons of AI tools that can sniff whatever they want from your laptop...
but no no no
English
@shakoistsLog Tell me you are not a developer without telling me you are not a developer
English
Thank god MCP is dead
Just as useless of an idea as LLMs.txt was
It's all dumb abstractions that AI doesn't need because AI's are as smart as humans so they can just use what was already there which is APIs
Morgan@morganlinton
The cofounder and CTO of Perplexity, @denisyarats just said internally at Perplexity they’re moving away from MCPs and instead using APIs and CLIs 👀
English
Announcing Copilot Cowork, a new way to complete tasks and get work done in M365.
When you hand off a task to Cowork, it turns your request into a plan and executes it across your apps and files, grounded in your work data and operating within M365’s security and governance boundaries.
English
Not knowing how to code giving you an advantage is absolute nonsense.
The more you understand, the better your prompts, the better the feedback you give, the better product you ship.
What will change is that the intricacies of syntax, compilers, module systems, the finer details of type systems, won’t matter as much to everyone.
But you should absolutely understand how the pieces fit together. From syscall to pixels. Learn how data flows, because you’ll be able to secure your systems. Learn about performance, because you’ll be able to push your agent further. Learn about APIs, because they determine how to integrate systems. Learn about how systems fail, because you’ll be able to make reliable programs.
English