Hacker News Reader

Comment by visarga | Hacker News Reader

> That forces people to look beyond the walled garden.

Every time I get "you used your quota, come back in 3 hours, or 2 days" -> that is experimentation time with their competition, leading to changed service plans. When they said "claude -p" will be billed at API pricing even for plan users I moved my harness off claude. After I integrated codex, then it was never going to be a full claude project again.

What business encourages users to try their competition and adapt their usage to the competing products?

View on HN

It drove me to setup Qwen 3.8 this weekend. I couldn't see the value in just giving them money for a higher tier plan instead.

I've never run a local LLM model before. Certainly won't take as long to iterate on this.

Qwen 3.8 is excellent. With the right harness, it does about 95% of what Opus can do, in my case automation software development. Since 3.8 came out, I have significantly revised my expectations for a local model. Give it another year or two, and we'll be running fast and free local models for nearly everything that matters, and these costly subscriptions will be a thing of the past. I've always believed that AI should be free for everybody, like TV and radio. We're almost there.

What harness would you recommend? I’ve tried Pi but the model struggled to stay on track after the compaction.

I have only 48gb of ram, so can fit only 80k context max, so good compaction is must.

I am running it on 32GB and I did not saw model loosing it context even after 4-5 compactions in pi. I am running sessions for few days sometimes. I think it looped once, but loop police extension stopped it. The only problem I have know is how pi compaction works, which is forcing full prefill which takes time and it is erroring a lot. I wrote my own compaction that should remove full prefil but it does not work. But this is the only problem with this setup and it is more problem with pi then the model. I much more prefer it to use Qwen then paid models: Claude forces me to do reauth every other day and codex models either are too costly or not capable enough.

Free tv and radio? Where do you live? Where I live you either pay taxes for it, alternatively, it is so ad infested that it is not possible to watch it.

I suspect the same will/is happening with AI. Either you will pay for it, or it will be so ad infested that it will become useless.

The claude -p thing was doubly stupid because they quietly allowed it again a couple of weeks later, so they pissed off developers for nothing

Wait, it's allowed again? Completely missed that. Been avoiding to use it and trying to find workarounds, not great.

I can't find the page now but yes they quietly "paused" the June 15th rollout of API pricing for -p headless. Presumably to come back again one day.

I think they didn't even bother making a separate post about their backpedaling, they just slapped some disclaimers onto the existing page:

https://support.claude.com/en/articles/15036540-use-the-clau...

Update June 15: We're pausing the changes to Claude Agent SDK usage described below. For now, nothing has changed: Claude Agent SDK, claude -p, and third-party app usage still draw from your subscription's usage limits. The previously announced monthly credit, which would have been available to eligible claimants in connection with these changes, isn't available. We’re working to update the plan to better support how users build with Claude subscriptions. When we have an update, we'll share it before anything takes effect.

Yes, they sent an email about it. You can also use the Claude SDK with an OAuth token ("claude setup-token" output) and it counts against the regular limit. Maybe they were afraid of losing users dependent on ACP (Zed editor and other compatible tools), since Claude Code does not have native ACP support and integrates only through the SDK?

> What business encourages users to try their competition and adapt their usage to the competing products?

If you are selling something, and losing $10 on each sale, you also would want to limit how much you sell.

I mean, sure, you are losing money on each sale so you can landgrab, but you still have to balance the land-grabbing with how much money you can actually lose.

>™Every time I get "you used your quota, come back in 3 hours, or 2 days" -> that is experimentation time with their competition, leading to changed service plans.

I guess this is why they're pushing Claude code hard (not supporting agents.md, not allowing third party harnesses, etc) but when switching to another provider is as easy as opening a new terminal and typing omp/pi/codex your moat is effectively zero.

They can compete on price, quality or value but anything else is just madness. Currently they (arguably) own quality but this won't last.

> What business encourages users to try their competition and adapt their usage to the competing products?

They are high on their own supply. The people running these companies are delusional imbeciles who have been placed in charge of billions of dollars.

Reply on news.ycombinator.com