
t
94 posts






agent-browser is now fully native Rust. The results: 1.6x faster cold start. 18x less memory. 99x smaller install. Less abstraction means faster shipping, more control, and capabilities that weren't possible before. Now with 140+ commands across navigation, interaction, state management, network control, debugging, and multi-engine support. It's become the tool we wished existed when we started building it. Thanks to everyone who reported issues, contributed fixes, and helped shape this release. More to come.


CANCEL your weekend plans. You NEED to: • Learn Claude Code • Learn Cowork (build 1-2 practical workflows) • Set up Perplexity Computer/Perplexity Finance • Optimise Cowork (plug-ins + skills) • Set up OpenClaw • Test Google AI products (Nano Banana 2, NotebookLM & more) • Experiment with basic agentic solutions (Manus) • Use AI to create a business plan/strategy/context files • Build an AI second-brain database (Notion) • Experiment with Notion Agents' *brand new* • Learn basic automation tools (MCPs, Zapier, n8n) • Learn prompt engineering - the better you can communicate with AI, the better your Outputs • Read AI articles • Dive into robotics • Research AI stocks/ETFs/investment arbitrages You have way too much to do...

Deploying a Rust tool to a 512MB RAM VPS and seeing it idle at 10MB usage is why we bother with low-level languages.


Saying not knowing how to code gives you an advantage in building software (thanks to AI) is like saying not knowing anything about filmmaking gives you an advantage in making films (thanks to having a smartphone + apps to edit stuff) Ignore this stuff and keep learning+building

> study kubernetes all week > learn pods > learn services > learn ingress > practice kubectl commands > feel ready for devops interview > join interview > confident > interviewer: "difference between udp and tcp?" > interviewer: "how dns works?" > interviewer: "what happens when you type a url?" > interviewer: "explain bgp?" > you: "i mostly worked with kubernetes" > interviewer nods slowly > rejection email next day



I am going to implement a Native Bayes classifier for filtering my spam emails in golang





High-agency (non-technical) vs low-agency (technical) talent is the most interesting disparity in tech right now


@JustJake how will a non technical person decide between thread::spawn and tokio::spawn? why is everyone in such a hurry to prove that computer science is the most useless degree?

@tarunnx Operationalizing AI tools to make their feedback loop of doing + learning faster And then core, physical competencies. Speedrun frontend -> backend -> os -> distsys -> hardware. You're gonna have to run really fast towards learning hard shit. Sorry, the timeline is hard rn









