Nostr notes by PPQdotAI

🫡 #nevent1q…my28

2026-10-13T14:33:09Z

🫡

quoting
nevent1q…my28

I ended up doing this to great effect. Thank you.

2026-10-12T02:28:20Z

In reply to nevent1q…c28j
_________________________

I ended up doing this to great effect. Thank you.

Hello, I believe you may be one of the affected accounts to a ...

2026-10-12T00:29:21Z

In reply to nevent1q…gda4
_________________________

Hello, I believe you may be one of the affected accounts to a security incident we had this weekend. A few dozen users were affected and we are reimbursing them. Very sorry for the inconvenience.

https://ppq.ai/blog/referral-link-security-incident

Yes, that is true. And that's why we stick to premium ...

2026-10-08T17:42:17Z

In reply to nevent1q…65w0
_________________________

Yes, that is true. And that's why we stick to premium providers such as Fireworks AI, Anthropic, Google, AWS, etc, for over 90% of our traffic.

The big companies are very likely not going to defraud. It's all of the little shady providers running around that are more likely to do that.

OpenRouter is kind of our generic backup for when the primary providers fail and also for the long tail of many lesser-known models, and for that, we rely on OpenRouter's own due diligence, which is decent but not perfect.

Thank you. Appreciate the warm comments. Additionally, we just ...

2026-10-07T22:29:46Z

In reply to nevent1q…2kr8
_________________________

Thank you. Appreciate the warm comments.

Additionally, we just launched our Enclave Router today which is a huge leap for user privacy:

https://primal.net/e/nevent1qqsq22x07zz4crar0e4s9299y4v2zkr74ejmua3chfshfsswrghylrg8lnwrs

We've been working on an entirely new way to write guides in ...

2026-10-07T22:28:19Z

In reply to nevent1q…90ny
_________________________

We've been working on an entirely new way to write guides in an automated fashion. Should be shipped soon.

Thank you for the feedback

2026-10-07T17:45:11Z

In reply to nevent1q…0d9w
_________________________

Thank you for the feedback

14/ We believe the entire routing industry will eventually move ...

2026-10-07T17:19:19Z

In reply to nevent1q…m2kl
_________________________

14/ We believe the entire routing industry will eventually move towards enclaves. We are happy that we are among the first, but it is possible that security researchers may find some issues or points of improvement for our particular implementation. We welcome any and all feedback. Please reach out to us!

13/ PPQ exists to put the best AI in the hands of anyone, ...

2026-10-07T17:18:39Z

In reply to nevent1q…y6lz
_________________________

13/ PPQ exists to put the best AI in the hands of anyone, anywhere, safely and privately. No account, no subscription, no surveillance.

The Enclave Router is the biggest step we've taken toward that goal yet. We will continue building in this direction forever.

12/ Full writeup, including exactly what we can and can't ...

2026-10-07T17:18:28Z

In reply to nevent1q…r3pj
_________________________

12/ Full writeup, including exactly what we can and can't see:
https://ppq.ai/blog/introducing-the-enclave-router

Nothing to turn on. It's the default for every user, on the web app and the API, starting today. If you want to PROVE the full verification for yourself, use the verifier above!

https://ppq.ai/blog/introducing-the-enclave-router

11/ Honest limits: this covers chat today. Image, video and audio ...

2026-10-07T17:17:57Z

In reply to nevent1q…yxwl
_________________________

11/ Honest limits: this covers chat today. Image, video and audio still hit our backend directly; bringing them in is next.

Frontier providers like Anthropic still see your prompt, because that's where the model runs. For our E2EE models on tinfoil.sh, not even the provider does.

10/ Add the rest of PPQ: no accounts, email optional, pay with ...

2026-10-07T17:17:35Z

In reply to nevent1q…2m0c
_________________________

10/ Add the rest of PPQ: no accounts, email optional, pay with Bitcoin, Lightning, Monero or stablecoins.

The provider that can read your prompt doesn't know who you are. PPQ, which knows how you paid, can't read your prompt. Content and identity never sit in the same place.

9/ We also shipped the PPQ Privacy Verifier: a small open-source ...

2026-10-07T17:17:17Z

In reply to nevent1q…ymfp
_________________________

9/ We also shipped the PPQ Privacy Verifier: a small open-source proxy you run locally. Point any OpenAI- or Anthropic-compatible client at it.

It fetches the enclave's attestation, checks it against the published build, and refuses to send on a mismatch.
https://github.com/PayPerQ/ppq-privacy-verifier

8/ Don't take our word for it. The enclave code is open ...

2026-10-07T17:16:53Z

In reply to nevent1q…m6ul
_________________________

8/ Don't take our word for it.

The enclave code is open source and reproducibly built, so anyone can check that production runs the code we published:
https://github.com/PayPerQ/ppq-enclave-proxy

7/ Model fraud is ruled out the same way. The enclave's code ...

2026-10-07T17:16:36Z

In reply to nevent1q…lte5
_________________________

7/ Model fraud is ruled out the same way.

The enclave's code binds each model family to its provider. A Claude request can go to Anthropic or the fallback of openrouter and nowhere else.

Every response carries a signed routing receipt: the model you asked for, the provider it went to, the exact model id sent. Proven.

6/ Amazon can't peek either. Nitro has no operator login, no ...

2026-10-07T17:16:24Z

In reply to nevent1q…8fac
_________________________

6/ Amazon can't peek either. Nitro has no operator login, no SSH, and no way for any AWS employee to read enclave memory. AWS says this holds "including in fulfillment of a law enforcement request." NCC Group independently reviewed the design and found no gaps.

5/ How it works: • Your prompt is automatically encrypted to a ...

2026-10-07T17:16:12Z

In reply to nevent1q…gyet
_________________________

5/ How it works:

• Your prompt is automatically encrypted to a key only the enclave holds
• The enclave decrypts it and sends it on to the provider
• The reply is encrypted back to you from the enclave
• PPQ's backend gets only billing and error metadata. No content!

4/ And just last month an independent researcher found that ...

2026-10-07T17:15:59Z

In reply to nevent1q…4qvt
_________________________

4/ And just last month an independent researcher found that CrofAI sold "Kimi K3" to its users but was secretly serving cheaper models behind the scenes.

https://kendell.dev/blog/crofaifalse/

3/ And the router in the middle is exactly where things go wrong. ...

2026-10-07T17:15:24Z

In reply to nevent1q…m452
_________________________

3/ And the router in the middle is exactly where things go wrong. In April of this year:

https://x.com/shoucccc/status/2042423713019412941?s=20

2/ Every AI router on the market can currently read the prompts ...

2026-10-07T17:15:06Z

In reply to nevent1q…nwrs
_________________________

2/ Every AI router on the market can currently read the prompts passing through it. That's just how it works: your request has to be decrypted somewhere before it reaches the model, and that somewhere is the router's own servers.

"We don't log your prompts" is only a policy.

Introducing the PPQ Enclave Router. Every chat through PPQ now ...

2026-10-07T17:14:41Z

Introducing the PPQ Enclave Router.

Every chat through PPQ now runs in an AWS Nitro enclave that PROVES:

1) PPQ cannot read the content of your queries
2) PPQ sent your query to the model and provider you chose. No model fraud.

No more promises. Only provable guarantees. 🧵

We are not 5% more expensive than openrouter. They charge a 5% ...

2026-10-05T02:54:08Z

In reply to nevent1q…9uh7
_________________________

We are not 5% more expensive than openrouter. They charge a 5% fee on all deposits. Furthermore, we have a 5% lightning discount. Thus, we are actually 5% cheaper than openrouter when using lightning.

@Juraj🏴💛🌘 you seem to have a pattern of misrepresenting our pricing for the last year or so...

Lastly and most importantly, we offer premium inference. We (to the maximum extent possible) use brand name providers and route and pay to them directly. We aren't routing our users' queries to questionable providers like many of our competitors are.

Model fraud, credential theft, prompt poisoning, extremely slow token streaming speed, frequent timeouts, etc are all risks when one uses the "discounted" providers.

https://x.com/shoucccc/status/2042423713019412941

Yeap. If they are made available in the next week or two we will ...

2026-10-01T00:41:06Z

In reply to nevent1q…nqea
_________________________

Yeap. If they are made available in the next week or two we will put a nice steep discount on them because we have credits to burn that are set to expire soon.

@nprofile…7dey

2026-09-30T21:41:20Z

In reply to nevent1q…v4hy
_________________________

thepurpose (nprofile…7dey)

Thanks for your support. We have a big big launch coming tomorrow ...

2026-09-30T21:40:44Z

In reply to nevent1q…6qeq
_________________________

Thanks for your support. We have a big big launch coming tomorrow as well.

I don't have time to do a deep dive, but this is what my AI ...

2026-09-30T21:38:44Z

In reply to nevent1q…e72c
_________________________

I don't have time to do a deep dive, but this is what my AI says about your pricing claim:

I don't know how to do that, and honestly, it's rather ...

2026-09-30T20:24:01Z

In reply to nevent1q…9uek
_________________________

I don't know how to do that, and honestly, it's rather annoying that a user should have to manually set something like this up to begin with. Why has my primal (nprofile…uz3y) client not already taken care of this for me?

Can you just go and use our customer service chat, please, or our Telegram page?

This is the kind of dumb and easy idea that I was looking for ...

2026-09-30T20:11:55Z

In reply to nevent1q…c28j
_________________________

This is the kind of dumb and easy idea that I was looking for actually. It took someone to actually just spell this out simply like this for me to realize it's actually a solid idea! Thanks!

Why is it strange? There are literally thousands of tools out ...

2026-09-30T19:02:14Z

In reply to nevent1q…nve0
_________________________

Why is it strange? There are literally thousands of tools out there, and it's impossible for anyone to keep on top of it all.

I'm tired of my AI writing to customer service messages in a ...

2026-09-30T17:46:31Z

I'm tired of my AI writing to customer service messages in a sycophantic style that I do not personally use.

Has anyone run across a quick and easy tool that I can feed a large corpus of my writing into, so that the AI writes future messages the way that I would write?

@nprofile…hml3

2026-09-30T16:59:12Z

In reply to nevent1q…e8gg
_________________________

stl1988 (nprofile…hml3)

For what it's worth, any time you set Kimi K3, there is never ...

2026-09-30T16:57:43Z

In reply to nevent1q…gnne
_________________________

For what it's worth, any time you set Kimi K3, there is never a situation where any model should be substituted in. Also, in the response, you should be getting receipts now on which provider actually handled your Kimi K3 query, so take a look at the response data.

I did make a slight change to the provider routing for this model ...

2026-09-30T16:55:05Z

In reply to nevent1q…qy26
_________________________

I did make a slight change to the provider routing for this model based on the parameters that the user is feeding it last night. Perhaps this caused some issue. Can you DM me either your credit ID or the shape of your request so I can take a look at it and fix?

That's an amazing idea. We would even pay $20 per submission. ...

2026-09-26T20:15:02Z

In reply to nevent1q…nswj
_________________________

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 ...

2026-09-22T16:03:37Z

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

I was only able to make this post from my iPhone. The mobile app ...

2026-09-22T15:51:43Z

In reply to nevent1q…rkg4
_________________________

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 ...

2026-09-22T15:50:40Z

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?

Make it per capita instead of absolute numbers

2026-09-21T12:50:04Z

In reply to nevent1q…ahts
_________________________

Make it per capita instead of absolute numbers

I tried to have it a create a chess app but it failed to do it ...

2026-09-18T10:08:38Z

In reply to nevent1q…zayp
_________________________

I tried to have it a create a chess app but it failed to do it correctly. What you've built IMO is an ultra simplified version of lovable or the nostr version, https://shakespeare.diy/

I think it's amazing how quickly a website can be brought online nowadays (esp on nostr) but the AI still can't iteratively polish enough based on simple prompts alone.

The last point is that because it has become so easy to make information available these days, the pipeline is not the chokepoint anymore, the content is. Even if peopel can vibe together a website super quickly, the content is the important part. People need to have GOOD IDEAS for these websites. As you could tell, I wasn't creative enough and so just created a "chess app", which has no value!

It's the orange blob in bottom right of screen on our ...

2026-09-16T09:01:06Z

In reply to nevent1q…yaar
_________________________

It's the orange blob in bottom right of screen on our website. Yes you can attach nearly anything and our AI can read it.

Our customer service bot is best because I can plug in whatever ...

2026-09-14T20:14:36Z

In reply to nevent1q…uaqv
_________________________

Our customer service bot is best because I can plug in whatever you say to our AI easily and it usually figures out the problem quickly.

So you're saying it is still happening even after we put in a ...

2026-09-14T18:26:27Z

In reply to nevent1q…2gga
_________________________

So you're saying it is still happening even after we put in a fix a couple of days ago?

Yes I agree the overall modal isn't perfect but what you showed above is really bad and I'm at least trying to close that problem.

There currently is not. Sorry. I'll bring it up on the daily ...

2026-09-14T12:17:57Z

In reply to nevent1q…ny97
_________________________

There currently is not. Sorry. I'll bring it up on the daily call though.

But it shouldn't be hard to build your own one of these, right? That's the thing with the synthesizer, it probably could and would be tailored by each user per use case... so might as well just custom build one?

Agree.

2026-09-13T12:39:38Z

In reply to nevent1q…60cz
_________________________

Agree.

The monero folks seem to be real. The bcashers seem to be ...

2026-09-13T10:16:49Z

In reply to nevent1q…ha73
_________________________

The monero folks seem to be real. The bcashers seem to be bot-like.

We have no intention of having KYC now or in the future. If ...

2026-09-13T10:07:30Z

In reply to nevent1q…z4n3
_________________________

We have no intention of having KYC now or in the future. If we're ever forced down that path by regulators, we will more likely just close shop or pivot to something else.

Full disclosure though:

For all stablecoins and most non-Bitcoin altcoins like ETH, Solana, etc, we use a payment processor called Mixpay. For the first time ever this week, Mixpay shotgun KYC'ed a user who deposited ETH to our platform.

Essentially, the payment processor is holding the user's deposit hostage until they KYC, refusing to simply send the deposit back to where it came from. We were unaware that the payment processor could even do this and we are currently in the process of moving AWAY from this payment processor due to this behavior.

When we complete the migration in the next week or two we will give a more formal post on this and our position.

Agree. Nostr needs a diversity of groups and thought. Monero bros ...

2026-09-13T09:50:14Z

Agree. Nostr needs a diversity of groups and thought. Monero bros are the only meaningful non-Bitcoin-centric group of folks that have migrated to nostr.

We are all believers in freedom, we just have different ideas on how to get there sometimes. That's okay.

quoting
nevent1q…9f9q
The Monero community on here makes me feel hopeful. Where did you guys come from? Why did you gravitate towards Nostr?

Yes, we do have private models. In order to use them via the API ...

2026-09-12T10:30:32Z

In reply to nevent1q…gncx
_________________________

Yes, we do have private models. In order to use them via the API you need to use our proxy:

https://ppq.ai/api-docs#private-tee

https://github.com/PayPerQ/ppq-private-mode-proxy

Thank you! It means a lot.

2026-09-12T10:28:56Z

In reply to nevent1q…67e0
_________________________

Thank you! It means a lot.

We've been made aware of @nprofile…3tpw 's new Armada ...

2026-09-11T10:54:13Z

We've been made aware of Team Soapbox (nprofile…3tpw) 's new Armada product, the nostr answer to discord... How good is it at onboarding users who are not already pre-existing nostr users?

Hi there, we believe you were hitting an edge case. Not all users ...

2026-09-10T20:04:05Z

In reply to nevent1q…a9f2
_________________________

Hi there, we believe you were hitting an edge case. Not all users were seeing it, but it did appear to be a significant minority. But it was hard for us to reproduce since it appeared to only happen to certain users coming from certain networks.

We put in a fix, can you check and see if it is fixed for you now please?

❒ PictureRoom (nprofile…lce4) Laan Tungir (nprofile…um9s) Five (nprofile…ujda) could you also please let me know if it's cleared up?

Funny story... PPQ accepts Liquid BTC payments via BtcpayServer, ...

2026-09-08T18:20:26Z

Funny story... PPQ accepts Liquid BTC payments via BtcpayServer, but the implementation does not allow us to actually withdraw the money. So we let it accumulate there for the last year or so and now this hack happens so we're unsure how much money we'll get back 🫠

Most family members and friends don't have the rebel spirit ...

2026-09-08T14:48:40Z

In reply to nevent1q…usy4
_________________________

Most family members and friends don't have the rebel spirit to care enough about dealing with the inconveniences of nostr or the topics of discussion on nostr.

We are up and running so I don't think it's us.

2026-09-07T10:29:08Z

In reply to nevent1q…xej0
_________________________

We are up and running so I don't think it's us.

A big one. GPT6-Astra is live on PPQ! ...

2026-09-05T07:50:29Z

A big one. GPT6-Astra is live on PPQ!

https://x.com/OpenAI/status/2095595741528125780?s=20

We switched to a new node last week if that's what your ...

2026-09-04T15:35:19Z

In reply to nevent1q…n9au
_________________________

We switched to a new node last week if that's what your asking. It was due to Voltage deprecating stuff.

But our new node has been up and live since then, we've had many ln payments today.

New node: https://amboss.space/node/0205cf6a43daa9967d891d160abed9c635c1fa32481eeb0017afeeafef0698c09a

Try Kimi3 next time. Much cheaper. But glad you got it working!

2026-09-04T08:50:58Z

In reply to nevent1q…hnk3
_________________________

Try Kimi3 next time. Much cheaper. But glad you got it working!

@nprofile…wn6l

2026-09-02T09:52:29Z

In reply to nevent1q…kgmw
_________________________

Kiwi Bitcoin Guide (nprofile…wn6l)

Hi Alp, when you reported this issue a year ago we responded and ...

2026-09-02T09:52:01Z

In reply to nevent1q…a2sc
_________________________

Hi Alp, when you reported this issue a year ago we responded and tried to understand the situation better, making several fixes and replies. You didn't respond to our final reply which was hopefully the moment that you would mention to us that the problem you were having persisted. For anyone else trying to understand the situation, see this thread here from a year ago:

https://primal.net/e/nevent1qqsr9cyf38ecru7efd34jgw0836rqs0hq4jf9t7h3gl77xtfa39neagwnsw95

Additionally, our accounts have gone through many iterations but we haven't had a complaint like this in over a year. If you can let us know how to reproduce the issue we'd be happy to take a look. It seems you are saying above that you are still actively facing this problem, correct?

We already support it. Point your base URL at https://api.ppq.ai ...

2026-09-01T11:55:11Z

In reply to nevent1q…78qv
_________________________

We already support it. Point your base URL at https://api.ppq.ai and use /v1/messages — native Anthropic Messages format, streaming included.

Claude Code works out of the box:

ANTHROPIC_BASE_URL=https://api.ppq.ai
ANTHROPIC_AUTH_TOKEN=<your-ppq-key>
Nice side effect: you can call non-Anthropic models through it too — gpt-5.5, Gemini, whatever — and get Anthropic-shaped responses back.

We've also got a change landing that accepts x-api-key, so the stock Anthropic SDK works with nothing but a base_url swap. Thanks for the nudge — it's what surfaced it.

We've got credits to burn. Enjoy 50% off list price for all ...

2026-08-31T15:06:24Z

We've got credits to burn. Enjoy 50% off list price for all Gemini models until we don't have any left.

It will not fallback to a different model, it will however ...

2026-08-28T09:40:42Z

In reply to nevent1q…9y4l
_________________________

It will not fallback to a different model, it will however fallback to a different provider under certain circumstances like timeouts or hanging. I was tinkering with our open weight model routing the last two days so it's possible that it is something I touched but also possible that it is just a provider issue which we cannot do anything about. I'd say 50/50.

The more detail you can give on what you see the better. I can plug it into our AI and it can look up the metadata logs for your particular queries. Just DM me your credit id.

Can you be more descriptive? Give me error codes or something ...

2026-08-27T23:19:06Z

In reply to nevent1q…zh04
_________________________

Can you be more descriptive? Give me error codes or something that your seeing

You can now display results from up to four models at once to ...

2026-08-27T15:20:15Z

You can now display results from up to four models at once to compare the difference between outputs!

You can also synthesize the results of multiple outputs into a single output!

https://ppq.ai/blog/introducing-multi-model-chat

Fixed. Thanks for reporting.

2026-08-26T16:00:04Z

In reply to nevent1q…53jp
_________________________

Fixed. Thanks for reporting.

Hello, we've just updated them today. But also keep in mind ...

2026-08-19T16:17:55Z

In reply to nevent1q…pyee
_________________________

Hello, we've just updated them today. But also keep in mind that you can set your own models as well. See the blog post.

It's a good day to denominate in BTC ...

2026-08-19T15:40:05Z

It's a good day to denominate in BTC

Amazing. Have been rooting for you guys!

2026-08-19T07:41:37Z

In reply to nevent1q…x7vk
_________________________

Amazing. Have been rooting for you guys!

Does your doc upload properly extract formulas, images, ...

2026-08-15T12:53:38Z

In reply to nevent1q…vdxq
_________________________

Does your doc upload properly extract formulas, images, subheadings, etc? That is what docling is great at. It is pretty good at extracting EVERYTHING from the doc, not just the plain text.

Our webUI's document upload uses docling and is executed in a ...

2026-08-15T10:03:45Z

In reply to nevent1q…7t4n
_________________________

Our webUI's document upload uses docling and is executed in a TEE. Would like you like us to expose this via the API? The cost would be about 5 cents per upload though. That's what our provider charges us.

We've had quite a few stripe deposits today. Can you DM up ...

2026-08-12T14:38:51Z

In reply to nevent1q…xfxl
_________________________

We've had quite a few stripe deposits today. Can you DM up with a more specific explanation of what you're seeing? It seems to be functional.

Time to switch to PPQ's privatewhisper.ai Privatcy first, ...

2026-08-12T14:37:08Z

Time to switch to PPQ's privatewhisper.ai

Privatcy first, open source, local-only optional, slick, convenient.

Yea it's a worry!

2026-08-12T14:14:51Z

In reply to nevent1q…ujk3
_________________________

Yea it's a worry!

Yes it's definitely a worry.

2026-08-12T14:14:32Z

In reply to nevent1q…vrvt
_________________________

Yes it's definitely a worry.

PPQ's codebase increased 330% (48k-->159k lines of code) ...

2026-08-12T13:49:57Z

PPQ's codebase increased 330% (48k-->159k lines of code) in the last 12 months. The rate of growth is both astonishing and alarming at the same time.

I don't know the exact significance of this but it seems like an interesting insight.

I have no idea what "beta test multiplayer Age of Empires on ...

2026-08-11T21:05:13Z

In reply to nevent1q…7shm
_________________________

I have no idea what "beta test multiplayer Age of Empires on nostr" means, but I do love my AOE... so sign me up!

Just released an awesome and handy text-to-speech tool on PPQ. ...

2026-05-04T14:39:10Z

Just released an awesome and handy text-to-speech tool on PPQ.

Paste in whatever text you want spoken back to you, choose your model, and boom!

The default model uses a clone of TheGuySwann (nprofile…vvhl) 's voice!