Simon

@ryanvogel Cannot be true if you’re still there

did OpenCode actually have mass layoffs?

🚀

@RedwoodJS None of my past contributions have been made with AI. Crazy how hard things were back then😉

RedwoodSDK and GraphQL are Built by Humans (Some of them are using AI.) rwsdk.com/contributors

It’s the day, if you want to build something small that can grow big, you have to try RWSDK

@RedwoodJS Historical moment captured live

v1.0 in progress: github.com/redwoodjs/sdk/…

if you feel fomo and you are sharpening your own ways of utilizing agents, you are fine if you feel fomo and you are trying to just feel better by thinking "ai companies will do the rest for me" you will be recked

@appfactory @RedwoodJS That’s true! I met Pete last week after 4 years since our SF meetup while he was visiting Montreal. Having friends everywhere in the world is a great perk of open source. 😉

open source is so wholesome, I've made some genuine friends in the @RedwoodJS community

If it’s simple for humans, imagine how simple it’s for agents.

🤔

@victorsavkin All of those at the same time

a) Programmers are just ahead. We build for ourselves first. b) Programming is a sweet spot: formalized, verifiable. Most people won't get agents anytime soon. c) I'm in a bubble :) Most devs don't use agents either. I'm confusing my circle for the norm. Which one is it?

When I talk to lawyers, doctors, manager,s their experience with AI is completely different from mine. Some use chatbots, but casually. Nobody is using agents at all. Three scenario of why this might be: ...

This 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file will make you 10x engineer 👇

whenever people talk about "shipping speed" they focus on 0 to 1 but what actually matters is how fast the team is still shipping a year into the project this is why everyone seems like they "ship fast" but nothing actually seems to be getting done

I find it very funny when anyone feels confident that they've figured out agentic programming, even funnier when they're trying to teach others how to do it. I've been working on OpenCode since May of last year and I still have days (like yesterday) where I'm not even sure any of this is a good idea lol I end up landing on "yes, these models are an incredible tool" but it's still all very confusing, lots of tangled thoughts and emotions and realities. I badly miss the mundane coding tasks that broke up my days/weeks, the ones where you put on the headphones and just bang out 600 lines of code. But, no question, replacing those hours of my time with a few minutes of waiting on an agent is a boost and worth being excited about, despite the mixed emotions. Then there's the distance that can creep in between you and the codebase if you start getting apathetic. I think it's pretty common at this point to make even small changes by prompting the models. It's less friction than finding the relevant code and making the change yourself. And less friction seems to win, must be some law of the universe or some shit. When most or all of your interactions with a codebase start flowing through the models, you start to lose track of where things live, which abstractions/components are carrying the weight, etc. It's a scary feeling to wake up and realizing you can't even reliably @ a precise file for a change you want to make, and you have to get more vague, leaning harder on the model. It all creeps up on you, there's an undeniable dopamine hit from using these things, and the resulting come down is predictable, like coming off a sugar high. On the positive side, it's really nice seeing other devs go through the same cycles, knowing we're all in this together and we'll ultimately figure it out.

@ahatzz11 @bengi_dev @justsisyphus You can read the doc

@bengi_dev @justsisyphus Honestly this is the worst part of opencode - the naming and nuanced differences and time it takes to really understand how to use it effectively is a bummer. After many hours it's closer to making sense, but I still don't feel confident i actually understand it all.

he knows how to vibe code but next time, try 'hephaestus' with codex- sisyphus is not optimized that much for gpt models hephaestus is like sisyphus for gpt models

Had a big migration that Codex absolutely bombed. Couldn’t even make the code compile. Opus one shot it. Both good models. Both far from perfect. You should use both and push their limits.

@juristr Same, but I use lazygit to see AI agent code change and make quick change via nvim integration. It become my main tool of review AI gen code.

👀 it starts happening... I coded a lot in the last 3 days but it just occurred to me that I never opened up an IDE 👀. - tmux with claude where I work interactively - Nx watching changes from Claude and running tasks - Nvim for quickly looking at files/quick edits

@esrtweet I don’t think the reason is some kind of existential crisis, but because the overwhelming load of events mix with the emotional roller coaster of using AI agents. It makes no sense how AI can be so good and so bad at the same time, the FOMO hit at each step.

If you are a software engineer "experiencing some degree of mental health crisis", now hear this, because I've been coding for 50 years since the days of punched cards and I have a salutary kick in your ass to deliver. Get over yourself. Every previous "programming is obsolete" panic has been a bust, and this one's going to be too. The fundamental problem of mismatch between the intentions in human minds and the specifications that a computer can interpret hasn't gone away just because now you can do a lot of your programming in natural language to an LLM. Systems are still complicated. This shit is still difficult. The need for people who specialize in bridging that gap isn't going to go away. As usual, the answer is: upskill yourself and adapt. If a crusty old fart like me can do it, you can too.

@garrytan I know you did that just to be able to say to Canadian founders to make an American incorporation once accepted to YC, and that’s fine. At least the message is well received that Canadians are accepted.

Oh Canada, don't call it a comeback! Thanks for your feedback. 🍁

@sindresorhus Your new service looks exactly like mine Great minds think alike!

Introducing my latest service: http://localhost:1337