X.KOJIRA.IO
Timeline

PayPerQ

[email protected]
npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h
Your provably private and premium way to access all of the latest and greatest AI models and tools. Pay-per-use, no subscriptions!
That's an amazing idea. We would even pay $20 per submission. I'll look into this.
The new Jev decision model is available on PPQ, both in the web app and the API. The web app is more of an introduction and exhibition. Most users will find use cases involving the API version:

https://ppq.ai/api-docs#decisions

https://blossom.primal.net/c95fc34b9d64084526362978c7e500…
I was only able to make this post from my iPhone. The mobile app is still working. I tried restarting my computer restarting, my browser, hard refresh, etc. nothing works.
I’m unable to view Primal from my desktop Web app for the last few days. I cannot see posts or create posts. There is just a big blank white screen. I can only see the sidebar on the left, but clicking things doesn’t do anything. Is anyone else experiencing this?
Yea I think it would send a long prompt to a model that can't support it... Has than been an issue on your side?

No, the three defaults are not the same.
IMO the current reason is to protect themselves from the Chinese who are signing up for subs in mass and distilling claude. I can't say if in the future they may try to force us to do likewise or not.

But I feel pretty strongly about broad KYC though and think I would rather just drop the models or pivot to something else then subject our users to this bullshit.
This issue is above my head but I do hear other users complaining about autoclaw in the last day or so. Can you let me know if/when this is fixed? I would really appreciate it.
Can you tell me how it is broken currently? We would like to address this imeddiately if it is something that is in our control.
Yes we have a 5% margin on anthropic through the API but the 5% lightning bonus offsets it.

We may have to make a bit of a change to that here soon though so there is some margin for us, even with lightning deposits.

The main benefit as you said is getting access to many more models and the smart routing as well. The smart routing saves bigly (50%+):

https://ppq.ai/blog/using-autoclaw-with-payperq
I also wonder if modifying the prompt, or guiding it in a certain way, could help a dumber model along.
Very interesting. I would love to do some sort of weekly Claw talk where people jump in and tell about their use cases.
Agree, I think we should somehow mention only UI queries. Do you use the UI at all?

Thank you for being a power customer!
Yes, just released yesterday.
Your autoclaw queries should now be labeled in the account activity. 🦞
I wonder if it would be better if "premium" were kind of a reverse in the scoring logic. Instead of looking for complexity indicators and giving it Opus, it could default to Opus unless simplicity indicators are present. That would be a way for it to always verge on the side of caution I would think.
Have you noticed if it tends to go for the more expensive model as the conversation gets deeper?
Yea I too would hope that it was designed to act with caution, opting for the better model when in doubt. I didn't write how it works though so just have to deal with it for now. Open sourcing it is a solid idea. There are lots of tinkerers that would make it better I think.
Noted on the labeling of the autoclaw queries. We'll do that.

What also may be of help is the ability to create multiple API keys now. Just shipped it a day ago:

The ability to generate more API keys via the API is coming as well.

https://blossom.primal.net/d98f11e622f473a180613b24e643ed…
nprofile1qy88wumn8… If you are using premium then it forces sonnet or opus for everything. So when you do 5+5 is going to use sonnet/opus. Additionally. I think it uses the entire context, not just your most recent prompt. So if your previous sections of that same chat session had more complex stuff, then it is going to use Opus and not Sonnet. That's why your seeing pure Opus.

I think the main issue could be that you are keeping a chat session open instead of switching to new ones with new tasks and questions. Lmk if that might be the case or not.


https://blossom.primal.net/d43968894cdf4cea4e329f78072ca0…
nprofile1qy88wumn8… read above notes not sure if you see them.
Additionally, caching is not a complex thing we are implementing on our side anymore. It is handled by the providers who know what they are doing. So the chance that we are doing something wrong due to the caching is not really possible.

It's mostly likely how openclaw itself chooses how many files it wants to read any any given time.

Perhaps the solution is to remove the premium option so this doesn't happen to anyone. Maybe there is never a need for premium.

But overall maybe the best advice for users is to not keep the same session running forever. Was that waht you were doing? Keeping the same chat open without starting new ones?
I don't think cache shifting is a thing. But timing is. As far as I understand how it works, it you run a simple query on an already long sessions AFTER 5 minutes has transpired, then all of the cache is gone. 5 minutes is the time barrier.

If you had premium set that simply means we are using opus and sonnet for everything, even if the query is simple.
Maybe we oughta just fork the repo we got it from and keep it open source so that we as a crowd can iterate on it.
The 15 dimension thing is mostly based on if certain keywords show up and then scores how many of those keywords show up and such. It's really not a complicated algo. But it's possible something unintentional is happening. I will look into this asap. Sorry for the troubles.
That is all junk. Refresh the page I updated the blog post 20 minutes ago.
Auto is mainly for use in the UI IMO. It uses an outside provider NotDiamond to determine which model to use. It's more general purpose.

Autoclaw's model pool is only a handful of coding models and uses different system to trigger different models. You can read in our blog post.
No, it's not that either. I need an AI agent to spin one up beyond the control or knowledge of myself. It's an experiment I'm working on.
Yes I need a bot to do it. No, it's not a laziness thing.
older →