返回首页
最新
Engineers are increasing setting up coding agents to run continuously, some running multiple agents in parallel. I've struggled to adopt these because I've struggled to build confidence without full code review.<p>How are y'all reviewing all this massive code output? How can it possibly scale, as the agents run faster or as you add agents?<p>I guess we'll have to learn to give up some control; we'll stop reviewing all lines of code, and increasingly rely on AI tools to summarize and flag specific lines. Are any tools good at this?<p>More generally, how do you build confidence in the code, both at the PR level and eventually at the codebase level (when 90+% of code in it will be written by agents)?<p>Am I too worried about code review, are there bigger bottlenecks in our jobs when using these coding agents?
<a href="https://x.com/revelium_studio/status/2009570090568577045" rel="nofollow">https://x.com/revelium_studio/status/2009570090568577045</a>
i'm interested to know more about the international payment system but most of the data online is looking more and more biased so I'm here to do recon<p>i'd love to know what's your preferred payment method for digital payments and why, any story you share would be great too<p>ps: please start with your country like<p>"US: <response>", it'll help me categorise better<p>thank u, in advance
Hey - I've been playing with LLMs since GPT-2 and recently experimented with fully generative UIs where the HTML/Canvas are generated just-in-time.<p>Every post on the feed( on slop/duck/storytime) you see is streamed and generated just-in-time with HTML and into a Canvas with Gemini 3 Flash.<p>Comments and DMs are bidirectionally linked with a Cloudflare Workers Durable Object which is why they feel so fast. Every generated post is saved into a DO SQLite which is then served into the "Following" feed so it can be served quicker.<p>This was inspired by Wikitok, a VSCode Extension I made around brainrot, and another fully generative UI site I made.