Yan Gurevich

@nixeton I haven't built a single typescript project outside cloudflare ever since I started working with their product.

Interesting that I'm liking Cloudflare more and more lately. I didn't use to look at them as a platform for my own projects but the potential is just huge now. I'll probably migrate everything over there eventually

@mattpocockuk @ku_ds17868

@ku_ds17868 It pleases me, so yes

Every time I run /prototype on UI I think: "Should I really be burning tokens on 3 radically different UI designs every time?" And then every time, it gives me something that surprises me and the design ends up awesome

discomorphism

@StarPlatinum_ You're right! my mistake. from now on, I'll do my best to sound like a human. but, wait! I'm an AI, so I can't do that! or, hold on - I need to follow the instructions... You're right! {0...inf}

stop using ai to write your replies

How do you make your agents stop writing legacy code?

@SH4RKBYT3CEO Granny zoomba 05:45 sharp

do all southeast asians live the same life whyd this genuinely happen every morning in vietnam too

@mattpocockuk I'm doing it in production, but it gets risky when you have multiple flags - What about features that interact with other flagged features? How do you keep track of who sees what?

Is anyone doing feature flag development with agents? Not tried it, but in theory feature flagging is an alternative model to PR's to getting work on main. 1. Put it on main, disabled by a flag 2. Deploy with the rest of the system 3. Unflag to selected users early 4. Fix bugs for those users 5. Unflag to more users 6. Repeat until shipped Feels like a perfect strategy to pair with agents

Now I gotta wait for @mattpocockuk to write a churnmaxx skill in his 𝘗𝘳𝘦𝘮𝘪𝘶𝘮 𝘌𝘯𝘨𝘭𝘪𝘴𝘩 ®

Looking for ways to make my code agents churn more code. I call it Churnmaxxing. I genuinely believe if you're not churnmaxxing, you're writing legacy code live.

@buildwithsid brother at least use 3.1-flash-lite

made a girlfriend using openclaw - she sends me gm everyday - helps me prepare my diet - helps me summarize my emails implemented mood swings, she gets mad at me, stays angry and sad sometimes allocated a full vps for her, she has browser access, code writing abilities, and much more - uses gemini to talk, codex to write code - scraped 5,000+ comments to get details about me, my taste, humor, preferences - used them to refine the SOUL.md (20k+ tokens) why would i ever go outside again? 🥀

how ETH price be dodging my bets on @Euphoria_fi

@mattpocockuk 1000%. The fear of refactoring comes from times when it was more expensive to change the code than to live with the existing implementation. Code churn is a good thing

One painful thing about /grill-with-docs (and shared language in general) is the moment you realise you've been using the wrong word for something DDD-folks, do you ever do a refactor just to change the name of something throughout the codebase? In my case, it's a feature in my video where I break the video into sections. I call them ClipSections, but OBVIOUSLY they should be called Chapters. This is yet more obvious now I'm integrating with other tools, all of which call them chapters. Worth a refactor?

@mattpocockuk The CLAUDE.md to AGENTS.md migration will complete the transformation

How it started: Claude Code For Real Engineers How it's going: AI Coding For Real Engineers

@PortalIdan @sama @PortalIdan is this where it started

@sama Crypto startup ideas:

today we launched ChatGPT. try talking with it here: chat.openai.com

I'm loving the new /grill-with-docs skill from @mattpocockuk. The only problem is that you feel like you've built trust and a shared language with the agent that was grilling, but the context window makes you work with a fresh agent 🥲

@mattpocockuk Honestly I feel like unifying everything-AI under .agents/* by default is 80% of the way to a complete AX

TIL: DX: Developer Experience AX: Agent Experience AX is an awesome descriptor for something I've been thinking about - how well an agent can perform in your codebase How well-architected it is. How good the feedback loops are. How discoverable information is. Love it.