Jonathan McDill

@0xIlyy Zellij > tmux

Please, stop running your agents in tmux. I just found out about Zellij and terminal multiplexing finally makes sense.

@caps_raunak When given the chance, most people will just go ahead and shoot up the steroids to get ahead, with little thought about the nasty consequences coming for them later.

AI is killing the grind. You work hard for years to get good at building apps. Make mistakes, fix them, build taste. Now one prompt and it's done. No sweat, no learning. Everyone shares it like it's amazing. But we're making real skills cheap and fake. Stop smiling and think about it.

@haider1 I can say “LLMs are so stupid,” and “LLMs are amazing,” very confident that both are true.

person: "LLMs are so stupid" > me: which model are you using? > them: free GPT-5.5, 16k context, no tools > pastes no context, wants perfect code > refuses to try current models: "just hype" > tries a modern LLM once > "oh… ok, this works" every single time...

@weswinder @dreamsofcode_io Convenient

@dreamsofcode_io i ain't no snitch

i looked at 12 different x accounts that constantly trash vibe coding almost none of them have shipped a product with paying users interesting pattern

@mattshumer_ @OpenAI Woah I bet you have something mind-blowing to show for it!!

Light work @OpenAI Apparently, I’ve used 3x the tokens of OpenAI’s highest user in just the last 17 days

@GaneshKompella I guess so. I was going off of this statement: "The gap between engineers is no longer who types faster." But I think in the end we agree. I just was stating that fast typing was never what made you a good engineer even in those ancient times before AI.

@jonathanmcdill You failed to understand what the post was about

The gap between engineers is no longer who types faster. It's who can hold a clean problem statement while Claude Code does the typing. Cursor and Claude Code don't reward fast hands. They reward sharp specs.

@pothuLabs Don't wake them up to this yet! I enjoy building things in a predictable "slow" way that improves, not erodes my skills. It's like this fun secret while everyone else is letting their brain rot, getting so "good" at playing the casino.

Is it just me or is vibe coding way less efficient than doing it the old fashioned way

@maxedapps It's like a savant toddler came in the room and started screaming and wrecking things but we have to put up with him because "he's got so much potential."

Supply chain attacks, broken code everywhere, mass layoffs that are justified "because of AI", stupid / dangerous AI-powered customer support (hi meta!), AI gurus selling you their latest skills and "must use workflows" ... glorious times :)

@MillionInt To figure out what is truely important one must do unimportant things

Everything in life follows from repeatedly answering a simple question: "what are the most important things for me right now?"

@codespicious Probably will be more complicated and unexpected than that. Also, which developers don’t use AI? Like 3 people?

Hot take. AI won't replace developers. But developers using AI will replace developers who don't. Agree or disagree?

@0xsachi If we need someone or some thing external to tell us if something is actually useful or good, we’re in a bad place

Is there a better way to evaluate models other than using benchmarks?

@kurtbuhler This is the little secret that the AI hype people don’t understand. When AI makes you unauthentic and unspecial you will be left behind.

I'm meeting more and more people willing to surrender their actions, style, voice, and even their thinking to AI. All its doing is making the authentic ones stand out more, and making me pay more attention to what they're doing and saying. Augment, not replace. Always.

@sriramsubram Trying to coax a magical thing that never quite does exactly what you want to build things is much more draining than building it yourself step by step.

AI coding tires you out more than manual coding. While AI coding does save time in some cases, it seems to consume more energy per unit time. The higher energy consumption is a combination of wrestling with AI and doing a lot more writing in the form of prompts. Both drain energy per unit one than manual coding in my experience.

@galluzzo_julian Welcome to the slop casino my friend. This is the “fun” future we’re in where the house always wins.

i wish AI never existed i wish I was still just making resources and videos for Webflow developers i wish i could still tell juniors 'just learn webflow and you'll get a job' i wish the skills I learned from 2017-2024 were still as valuable today as they were before but the cat is out of the bag and it's not going back inside, so i choose to adapt myself for the future are you still living in the past, or are you adapting for the future?

@harshilmathur Code is a set of instructions that the computer runs. Skills are markdown files full of hopes and wishes.

“Skills are just Markdown files.” Sure. And code is just text files. Compilers gave code power. Agents do the same with skills.

@hasen_95dx It’s like people have forgotten all the lessons of the past because… new shiny thing.

Plot Twist: introducing AI coding at most large companies will result in increased costs and delays "Adding more people to a late project makes it later" "Adding AI agents to a dev team makes it slower"

@Howaboua Especially in a time when manic velocity-at-all-costs is portrayed as some sort of moral virtue

@jonathanmcdill don't we all? The hardest of them all!

Stop moaning about Codex limit and: 1. Switch off subagents 2. Stop using /goal for stupid shitposting on X 3. If you must, get a 200 sub. It's for powerusers. 4. Switch to Pi. 1k tokens startup cost anyone? 5. SLOW THE FUCK DOWN

@richardartoul Honestly I have this experience a lot. Not always, but sometimes it really seems like I spent more time using LLMs with less understanding of the code and more frustration. But you’re not allowed to say these kind of things these days. It might hurt AIs feelings.

i'm on the verge of giving up on LLMs for code generation they're game changers for code review, writing tests, and debugging, but I'm starting to think the juice isn't worth the squeeze for the actual code writing 95% of the time