Opencode vibe codes and releases like 3 projects a week at this points. Cool, just know its throwaway software to them. They seem really reckless when it comes to security. Opencode V2 basically threw security out the window. Theyve completely lost the plot as an org.
Their CEO spends all day on twitter talking about how much better he is than everyone. And how nobody can use agents like he can. Its quite obnoxious
Also just use CDP, way too many browser solutions for agents when chrome ships with the ability to control the browser at a low level.
If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm, point them at a pkg thats uses CDP like go-rod.
> Their CEO spends all day on twitter talking about how much better he is than everyone. And how nobody can use agents like he can. Its quite obnoxious
I follow him on X, and I never got that impression. He has always come across as a skeptic IMO. Often wondering what others know that he doesn't due to practices that he hasn't found useful. I think yesterday he posted something suggesting that he doesn't follow usage patterns posted by others because the models have advanced to the point where any perceived improvements are by model rather than these patterns. I generally agree with this, and try not to get attached to any way of working with these things.
As for the usage of OpenCode, I have kept it to a minimum. V1 memory usage got a bit wild. Not sure if V2 has greatly improved. I have signed up for their Go plan a few times for times when I get tight on my other subs.
These guys have been building amazing and useful products for years.
SST was a tool ahead of its time when it launched (I used it). It’s on version 3 and is now open source and community maintained. I’ve found it useful.
The OpenCode agent is very cool and they even host some of their own models via a subscription. I found it useful too.
I haven’t used this new one yet.
Have you built anything useful, or are you just a critic?
You sound biased for someone who's hardly used the product.
Yes I put in 12 hrs a day, and usually running overnight as well in maybe half a dozen containers. I have billions of tokens going through Opencode a day as my main harness, for atleast a year.
I cannot accept their security model in V2 nor am I willing accept the nightmare and dangerous process of an upgrade. Where they basically tell the user, it ships with no permission model your plugins wont work, and we're making arbitrary changes all the time because we dont like how something is spelt/is plural that break your config. Typical vibe coded changes that are made for no rhyme or reason that are pushed without care so the user deal with the headache. V2 is literaly slop because they got obsessed with full on vibe coding.
Instead of having a version bump to V2 that cared about backwards compatibility they said screw the user, we have llms now just tell it to upgrade your config and ask it to make no mistakes, we provided a skill, good luck (oh, and by the way we no longer ship an easy way to confine the agent into a directory, thats on you good luck.. Ask the llm who now has access to your entire computer, make no mistakes).
This wouldnt be that big of a deal if I didnt have half a dozen different sets of configs with granular permissions, each with their own plugins for different clients Im working for. Its probably a multi day task to upgrade for any power user which shouldn't be the case for any piece of software's version bump. If Im going to take the time to upgrade it would be to a different harness all together.
Oh and by the way, when you turn off acess to the internet to a container and use a local model, session titles suddenly stop working.. Turn it back on and they start working even with no Opencode acct authenticated, because they're summarizing your conversations without your consent to derive session titles.... So who knows what they're swallowing up of your conversation data idk, I should put it behind an burp and see.
They have 2k issues on github but are shipping native UI frameworks nobody is going to use, for twitter likes.
They got a bunch of their users keys stolen and never took responsibility but rather blamed it on "distillers" instead of their own internal policies that lead to it. You can thank Dax for how every AI company scapegoats all their failures to distillers now whenever they fumble your credentials.
Thats too bad, its the equivalent of being a gun manufacturer and opting not to put safetys on the weapons you make. I dont really trust their team tbh. I'll stay on v1 for now until I find time to migrate to a different harness.
This is pretty alarming. I try to set up my containers to only have web access via specific provider MCPs and not just free reign to the open web. I would not want to use a harness trying to fight against me on what is already a very hard problem.
I feel very validated to hear someone else rant about the v2 upgrade as a user of OpenCode. As a user it left me wondering
"If AI is so great at coding, and you're so good at using AI, why can't you make the changes you want in the v1 codebase gradually? Why can't you use AI to solve (not just mass close, actually FIX) the thousands of open issues you have on your GitHub?"
I think this is making me realize that I don't want to keep using OpenCode after using it as my daily driver for over a year (thousands of sessions).
And before anyone says "use Pi, it's great", I tried it and while it is fine, I think I fundamentally don't want to use a node-based tool ever again. Don't know why, they just always feel "slick" in all the least useful, most flashy ways. Anyone have any recommendations for the "sublime text 3"/nvim of stable and reliable harnesses?
> I fundamentally don't want to use a node-based tool ever again
These are not (nostly) written in JS/TS, so I think these are not node based.
https://github.com/openai/codex (this is rust but I don't absurd dependency depths rust seems to be getting, so in that aspect rust tools is becoming like npm tools)
As for how reliable these are, you'd have to try them and see for your own usage. I am sure there are more. Lighter ones, maybe less famous, but I have tried these and I am back to using Claude Code most of the time :D. Though I am trying to get familiar with Goose. However given a choice between OpenCode and others, I won't even bother with OpenCode – it's really that bad. Though I've their Go plan and that has been very userful for me (super vfm).
I also don't get the point of Pi. Pi either has to become Claude/Codex for most coding tasks and then what's the point it, otherwise a tiny harness (or script) replaces it, so I've also stopped using Pi. Apparently there Pi ports in other languages.
I found this to be too minimal, but I would try again. Are there any power users of it that have written up? The thing is I do like plugin-esque paradigms.and I do need mcp functionality.
> And before anyone says "use Pi, it's great", I tried it and while it is fine, I think I fundamentally don't want to use a node-based tool ever again. Don't know why, they just always feel "slick" in all the least useful, most flashy ways. Anyone have any recommendations for the "sublime text 3"/nvim of stable and reliable harnesses?
I really don't get it, since Pi has always been "vim of harness space" for me...
I am referring to "craftsman" software: it covers broad range of users flows well (from generic on-boarding, to very specific feature that rarely used), with generic user behavior modeling so it "feels" natural when reveal features progressively, with proper animation in-between to visually guide user's mental model of the software itself.
These are gone, not because the generic "enshittification", but because with the new-wave of software, there is no need to "model user behavior" or guide "user metal model" any more: user tells exactly what software they want, based on what their mental model is. There is no need for such craftsman software any more.
They have raised close to 1B and it seems financially they'd have raked in already a lot. Their subscriptions are gong quite well it seems – it's really cheap. So I am not sure they have lost the plot as an org for themselves. As for losing the plot as an org for its users – don't think that was the goal ever. Go to their GitHub to see for yourself. These guys inserted themselves into the "og" OpenCode and then left with the name because they had registered the domain name and made a much inferior TS clone and made it famous which is all it counts in today's time. Job done.
> Also just use CDP, way too many browser solutions for agents when chrome ships with the ability to crontrol the browser at a low level.
> If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm, point them at a pkg thats uses CDP like go-rod.
As someone who has vibe-coded my own such wrapper, I think that there is a lot of value in having a common interface for an agent to interact with CDP beyond just slinging together ad-hoc scripts until something works. CDP exposes a lot of features, but exposing them to an agent in a sane, consistent way takes a good bit of work.
It's also taken me a good bit longer than 4 hours by now. The features really add up over time.
He runs Opencode and major stakeholder in the parent company. They don't too publish an org chart. Just because you dont give yourself the the Chief Executive title doesn't mean you aren't the Chief executive. Thr not a ceo thing is kind of a twitter meme too, hes the guy in charge.
> Their CEO spends all day on twitter talking about how much better he is than everyone.
Not that agreement proves anything but I am glad to know I was not the only one. Him, Boris, Theo (t3.gg or something) -- I look at their archetype and wonder if that is what you need for success and if indeed that is what you need, then perhaps I do not want success at all.
It's interesting because it's not strictly speaking needed.
You have people who have high visibility on social media without playing games or constantly exaggerating their accomplishments or work.
But you're right that people who do play these games and adopt your so called archetype end up with this much visibility.
I think the reality is as simple as grandiose claims or presentation or just being clickbait personified works to gain an audience. It's also why these people have a bigger ratio of fans to people who can't stand them.
The much rarer people who reach a large audience while remaining genuine tend to be much more universally liked. The ratio is better for sure at least.
it's been this way for years tbh. they made the whole web scene insufferable. the few gems have remained in the web scene, while everyone else moved to ai.
They see success publicly and seem to be drawn to it like flies on shit. I mean look at the drivel and pure propaganda that Garry Tan posts on X still. It's like money gives you a pass to be a raging lunatic.
>If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm
isn't vibecoding a throwaway integration like this what you're criticizing opencode for here? why would i waste my tokens on that when opencode will give it to me already built?
Yeah I've been somewhat disappointed with opencode lately (not as disappointed as I am in codex though)... the issues and PRs on GitHub are continuously accumulating and they don't seem to have any structured/efficient way to deal with it. Obvious issues with obvious fixes, and zero disagreement are sitting so long that they just get auto closed after 1 month.
I kinda expected things like this to happen the week of the Anthropic IP0. EA sees everything as a trolley problem anf tries to create them wherever they can. Thwy will mess with critical infra to get themselves the regulation they want.
Its a pet conspiracy, that I know has no evidence, but EA would love to get the public in agreement with them on AI so that the public consents to them being the arbiters of AI regulation.
I love how Americans are so brainwashed to think the Chinese can't innovate without cheating, while they lap us in basically every category possible except this one verticle, that we had a 3-4 year head start on.
I partially wonder if the Chinese would even release a model that flat out beats Claude/fable I say this half jokingly...
but I imagine there's part of them that goes "These Americans are so delusional about how language models are dangerous/existential threats that they might kill us or hurt our economy over a chat bot"
It could also just be they're far more tactical. Deepseek generates a ton of revenue because its practical/economical. You do not a mega super PhD assitant to build your 4 MAU SaaS app.
Anyways I hope China wins this pointless AI war, because if it does lead to innovations in medicine and science I would much rather the Chinese be the ones that discover those things than the US billionaires who'll almost certainly try to make as much money as possible.
No they wwont, they'll never be maintained. Theyll decay with their vibes. People who vibe code whole swaths of software are'nt capable of caring enough to maintain it. Llms mostly make smart people lazy and or stupid.
I used Claude to document the wire and firmware protocol for an expensive piece of equipment I own where the only software available ran on PowerPC OS X.
Is this just "vibes"? Maybe, but I now have a full, verified spec, against which to build software for myself, also with a little bit of "vibes".
I'm currently teasing apart numerous ancient Text to Speech synthesizers with Sol and the amount of times I ask a follow up question that forces it to correct 5 things it's already said/documented is ridiculous.
You would have tell you. My point is that it's clearly less than a true verified spec. Even in a harmless area like mine, it's at least horribly obnoxious. Not worth too much to me because unlike you I do have papers and open codebases to study if nothing else.
But this is your unspecified expensive device. A verified spec wouldn't have you send a command or configure a table that bricks or damages it. A vibe verified spec very well might. How much is that worth to you? What are you willing to lose?
The spec was derived from disassembling/decompiling the firmware and two host applications and one diagnostic application. The firmware source C was then reconstructed, and using the original compiler/assemlber/linker a byte identical firmware build was produced.
This all occurred after recording on the wire traffic while running the equipment with the original software, against which the spec was verified.
> How much is that worth to you? What are you willing to lose?
Well, nothing is free I suppose. And I was willing to take some calculated risks in order to reach the goal of new software.
I'd say 100%, since it's a spec? what's a spec worth if we don't know how accurate it is? this isn't exactly a post apocalyptic world where even junk is valuable
I wouldnt say implementing an official spec with an llm is vibe coding.
Hard to judge though, most people are just winging it though and shoving it out the door as if its impressive.
But yes, I think its probably bad because you probably didnt learn all that much and became more reliant on Anthropic. Unless you dont care about learning, then who cares.
I've had my 99% vibe coded Hazel replacement running for almost a year now. Still works.
Same with my bespoke IRC client, RSS feed hydrators and a dozen other small utilities I've vibe coded. All stuff that I've been planning for a long time, but haven't found out the time to dedicate to them.
Now I'm saving actual money every year because I could drop subscriptions applications.
Not every application needs a weekly release with new groundbreaking features. They're just one and done. Maybe an update if you hit a sharp edge while using it.
I can add features and make it work just the way I like it. I've been on IRC since the 90s so there are some idiosyncratic things =)
It's not a massively complicated thing, just a single server that says online 24/7, which talks using a custom protocol to different clients (Web, CLI, Linux native and macOS native).
I could've used pre-existing software to do most of it, but there's always jank and things I can't customise without trying to get changes into the mainline.
There are many IRC clients and this one is mine. I'm not expecting anyone else to use it. It won't have a community, a snazzy web page and it won't be taking in any issues or PRs from anyone =)
Vibe coded software is currently already better than half the developers out there. Accept it. Code won't be seen anymore. It's a skill only a handful of jobs require to have.
Actually, most things dont run in a browser. I know you probably live in that world but its not a handful.
Just because you've chosen to turn off your brain and prompt your way to whatever, and your 10 MAU app works fine does not mean large systems, critical devices and critical infrastructure's code will no longer need reviewed. Sorry your dad's pacemakers firmware code, and the ancillary systems that enable its development will need its code reviewed. Along with aircraft, satellites, municiple traffic systems, countless medical devices ect ect. I could go on forever.
Not everything is non serious SaaS platforms with little users. Just because you have success writing slop that exists under no load, and nothing relies on it doesn't mean the world is now different.
You have SEVERE dunning kruger syndrome, and unfortunately a lot of other people have this same ailment and the worlds systems are decaying as everyone turns off their brain and offshores everything difficult to language models, because humans like you are lazy and will always try to get the free lunch that doesn't exist. People will die because of this attitude.
There are a few steps between "web page" and "pacemaker" =)
Also I know at least one satellite company who definitely uses AI-assisted programming (I interviewed for an AI-heavy position in there).
Also in the mobile gaming industry AI is not even optional nowadays, every single AAA household name game has "AI" in it at every level - some used AI when it was called just Machine Learning.
Lmao if a company starts shipping llm documentation for its products so you can tamper with them, you should assume youve woken up in a parallel universe.
I think most people on here fail to realize the demand to customize and build things hasnt gone up. Just because llms exist now doesnt mean normies all of a sudden want to start getting into programming, they dont care.
The only number thats gone up is people who were slightly interested in programming/CS before but were too undisciplined to learn things themselves. Llms are great for those lazy people.
My dad, who is in his 70s, recently started recreating a piece of audio visualization software from the 00s using Codex. He’s having the time of his life! He was never interested in programming/CS. He just wants his software back.
I get the point that you're trying to make, but it's not just people who were undisciplined. I spent many years developing code projects that I remember spending hours every afternoon just to ship a single feature, and that pace has obviously changed.
I still get the joy of translating ideas and orchestrating and architecting solutions to problems I have in real life, but just at a quicker pace.
If some of those tools and solutions can help other people, that's great. If not, that's okay too. I hope everyone sort of has that mindset who's building today.
>The only number thats gone up is people who were slightly interested in programming/CS before but were too undisciplined to learn things themselves. Llms are great for those lazy people.
How is that the same thing. Lovable didnt get hacked.. Also hint, there's nothing scary about ablit models, they dont increase someones capability to hack something with AI just reduce annoying refusals, purely ergonomic.
Each psychotic vibecoder making 50 slop projects on an account. Also probably counting demo projects. Idk, if I had to bet against any company it would be lovable.
But they have tons of VC money so they'll get aquired by someone in the incestuous circle of SV investors.
non-tech founders, small businesses, non-tech freelancers, everyone on budget who cannot afford hiring a dev and a designer and who wants something fancier than classic CMS.
Those people can very easily make a website all on their own using the latest models. It will be cheaper and higher quality.
Yes you will need SOME technical knowledge. But people are just lazy. Everyone can learn this stuff. Just ask any anthropic model how to deploy a website, it’ll tell you.
It is wrong to blame non-professionals for the failures of professionals. No, technical knowledge must not be required. No, people are not lazy, they just do not know where to start and may have incorrect assumptions about that. As a consequence, they may write a wrong initial prompt and end up with the same solution that Lovable offers or even worse, despite using the best in class model. This situation is not specific to Lovable or AI in general, it was always like that with end users and always the solution was to help them, not to demand from them to adapt.
Yeah I just disagree fundamentally, complex things require a level of understanding. We can only goo-goo ga-ga dumb things down so much until they stop being useful. What makes web applications useful is the inherent complexity in the web. If it were simple, nobody would use it.
Like, I can't meaningfully work on the engine and transmission in my car. That doesn't mean that we should dumb down my car and replace it with a Fisher Price toy car that I CAN work on. Because that wouldn't be useful to me.
So, what I do is I go to professionals to work on my car. And, I do research, and if I feel confident I can do something, like change my spark plugs, I do.
When you build software there is always going to be complexity around the implementation. Security, data distribution, coordination, deployment. Always. When you dumb things down, what you're actually really doing is making assumptions. If you make enough assumptions, congratulations - you've built an app. Now it's suitable for end-users.
When it comes to using an LLM to make an application, it already makes maybe a few billion assumptions for every prompt. If it makes any more, it wouldn't be useful because now it's not making an app for you, it's just delivering an already existing application.
Yes, if people want to build things, you have to kind of know how to build things. That's always been the case, forever, in every field, across all of human history, with no exceptions. Why would we think it's different now?
Their CEO spends all day on twitter talking about how much better he is than everyone. And how nobody can use agents like he can. Its quite obnoxious
Also just use CDP, way too many browser solutions for agents when chrome ships with the ability to control the browser at a low level.
If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm, point them at a pkg thats uses CDP like go-rod.
reply