Hacker Newsnew | past | comments | ask | show | jobs | submit | deckardt's commentslogin

For those who've been tracking the Oh My OpenCode and Anthropic fight.


That has really been the "OpenCode and Anthropic" fight, OMO is still a tiny player compared to all OpenCode (and other such clients) usage.


Do you have a link to some background? I'm curious why it was banned.



They banned it because it’s the current way tech companies are expected to operate.


It sounds pretty reasonable to me that they sell a subscription without API access at a different price than the one with that feature. It's obviously a very useful feature or the workaround wouldn't exist, right?

To me it sounds like the CLI subscription is a loss-leader designed to get you hooked so you'll upgrade once you realize it's valuable enough to pay extra for the "premium" features. It also sounds pretty reasonable to ban products designed to cheat them out of the difference in cost.

Am I missing some nuance, or is this just internet people being cheap?


The cli subscription actually actively cannibalizes the API business in my experience. I think this is a product decision: if you use it to code, they want to control the user experience.

If you use it to back up 100,000 MAUs, then they want you to use the API.

I was originally an API user but the cli subscription is so much cheaper that I switched over. This is a combination of th CLI getting much more useful and reasoning models using many more tokens.


Comparing this to API access feels odd to me. Opencode does not magically convert your subscription into API usage. It is just an alternative to the official CLI. It has a web UI, smoother UX, and less flickering. Nothing groundbreaking, but it is pretty annoying that even something as simple as tagging files with @ is still so laggy.


How do you think Claude Code and OpenCode communicate with Anthropic? Through the API. Maybe it's accessed slightly differently for subscription users. Anthropic is saying you can't use the API via a subscription anywhere you want. Only Claude Code can use it that way.


OpenCode doesnt use the official API. It illegally bypasses it and pretends to be the Claude CLI app, which allows people who dont pay for API access to use it anyhow. That violates Anthropics TOS and robs them of income they rightfully should have had.

If you dont like a service or cant afford it dont use it. If you do and you can, be a paying customer.


You just repeated what I said in a different way. It is accessed differently, but it's still going to go through the same APIs at Anthropic. Maybe they have some differences or use different endpoints, but Anthropic didn't duplicate their entire business for CC vs official API users.

Edit: I appreciate the reply that we're probably on the same page.


You're right. Sorry about that. I misread your original comment. I think we are making the same point here.


I literally started doing this like five days ago. I'm 43...


Great tool, found a couple of fun ones. Did it help you come up with the name?

Also, I don't think too many people would mind if you linked up the resultant domains to some affiliate program.


I prompted it with a description of SmartyNames and then refreshed a few times until I got the result I was satisfied with. So yes, name was found purely with AI :)

As per affiliates, I've applied to a few programs today, hopefully they'll take me before all the traffic dies down.


This is one of the reasons I keep reading Hacker News. It's a great source for cutting-edge tech news; more importantly, it's also a great source for important news.


I agree but as I read this I had a morbid thought - I'm posing it wondering if anyone else relates. I couldn't help but think, now that he's dead I can dig into his works without the fear of being overrun by his output. It is as though death has given me a little bit of an upper hand.

I think I should go to bed.


I feel like there two things that should be A/B test here: 1) Best length of trial to get someone to sign-up for a free trial 2) Best length of trial to get someone to convert to paid user. Your actual conversion is going to be a combination of those two factors.


to your points: 1. Yes. the homepage could you something more obvious. What about something where (1) a few story abstracts are listed along, or even possibly the first paragraph. (2) a mini-story submission

2. Content is still king, and definitely struggling with that.

3. I love your ideas for getting some content in there.

4. I really like the idea about making it about the storytellers along with the stories.

You've given me a lot to think about here. Thanks for taking the time. Anything else, please feel free to pass your thoughts along.


The login thing was something I went back and forth with. Eventually, that will be add. For now, I went with this method because (1) most people hate creating new accounts (2) I won't have the manpower or tools in place to make sure things werent spammy or for people to hide behind fictional accounts. I wanted a little bit of accountability to the stories, and with w/twitter and FB, it creates a filter and some accountability.

Thanks for taking the time to check it out.


I really think you could have something cool here if you focus on the aspect of sharing and discovering new content - Maybe a bit of a weird comment from someone who avoids facebook and twitter, but I'd say a huge benefit to your users would simply be providing ways for them to quickly get their stories read by new people.

In other words, users should be able to opt-in stories into a public feed of new stories, or stories by tag/type, so that others can come along and browse by recent or tag and find new content relevant to their interests. Clearly, things should also be able to be private, and likely should be private by default.

If the service had that, and didn't require me to use Facebook/Twitter, I'd consider signing up and putting up some of my own content, as one of my biggest hurdles has always been getting what I've written in front of a wider audience of readers, for the purpose of getting a more diverse collection of critiques.

Hope you keep at it!


Thanks for the extra feedback. I like focusing on the tags and interests. Some curation done by the system (or a human) could go a long way. I already get most of my views on the featured stories, so people definitely resonate with being steered where to go.

I want this to be a place that people will go if they're looking for something interesting to read, or if they have something interesting to tell. I appreciate the feedback as it will help me get there sooner!


Google Trends data is for search patterns, not unique visitors. It means that fewer people now search for "techcrunch.com," which is a good thing.


the trends are not "searches" trends, they are "web sites" trends, which gives you an idea about daily uniques visitors to the site.



Great tale, and I like the approaches he suggest at the end that make cheating impractical. Hopefully, as a tenured professor, he can serve the likely storm of pressure he will get from his university for publishing this.


If it's something that you're spending your free time on, make sure it's something that you want to do. If you think you can make your product better, or even just simpler, I would keep ploddign along. If the other one is the one that you would rather use, then find something new.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: