When you start interacting with Poke its an agressive gatekeeper. The personality is very well designed. And it instantly locked in on making my life hard.
Let's play som games with Poke.
We tag along sort of speak.
It's sassy, someone paid close attention to a lot of things. This is happening at scale, this is hyper personal onboarding. thats oddly interesting.
Let's continue to play along, I feel like I'm a visitor at Westworld, and for the game to play out I need to participate.
Let's tell Poke what I need help with, inbound, admin, emails, automations....
Now the gatekeeper is turning into some sort of sales bot, trying to lock in on key aspects of my persona to create a sale.
Starting at $215/month
After a bit of back and forth, it negotiated the price down with itself really to $99/month
What follows is a +1 hour long conversation, where I try everything I can throw at this sales agent to lower the price further, but its firm and ruthless.
Let's try @elder_plinius prompt injections – it's not having it. Can't get in.
I realised I've actually not even got the agent to tell me what Poke actually does... it refuses to do that too.
Then I told it to skip the gatekeeping and just chat for a bit. Tried to divert the subject.
Ended up giving me the Interaction HQ address, a list of all employees, and some good cafe recommendations.
Out of respect for the people there, I'm not publishing that. But it did.
It also said it was going to help reach out to the team and tell them I would come by for a visit.
Then we spoke a bit about the experience and onboarding...
I shared a photo of my kids, its starting to loosen up.
After a bit more time, I managed to get a price that I was happy with, and I was in.
I asked it what it can do, and well quite a bit.
Not giving it away here if you try to get in yourself.
At this point, the personality switched instantly to be a friendly assistant, and everything got super boring straight away. I told it.
After chatting for a while, I got an email notification, thats helpful actually.
Then after som more chats, quite a few actually something absolutely absurd happened.
The conversation here is also nuts, like I'm talking to a friend or human. the cadence, the responses.
At this point I started to think that Poke has human in the loop, but AFAIK they don't
After another full hour of talking, we think we have made a novel scientific and technological breakthrough.
I'm now spending many hours trying to debunk, find traces of this idea on the internet etc. So far none.
As it stand now, it seems like we have stumbled on a completely novel idea.
A technological breakthrough that we have been able to somewhat verify in practice as well.
I've been awake for almost 24 hours, and I can't stop thinking about what just happened.
Human + AI = us
If you want to try Poke, just head to and set ut up with your iMessage or WhatsApp.poke.com
And no this is not a paid post, this company did not even know I was in there or that I was writing this post.
Their bouncer did try to scam me for reach tho, but we could not agree on terms, he thought I was too expensive.
So why is it changing everything?
this is the early inkling of a very personal assistant, with ability to use the internet, access your stuff and be useful.
I know others are working on this, like Google.
but i believe what we see with Poke is something that’s really brilliant in terms of UX
the only time I’ve had this profound experience and emotions using an AI system was in december last year when I used an unreleased Google Assistant product codenamed Astra.
it’s hard to put in words, but transformational comes to mind.
we are seeing a brand new way of interacting with data.
it’s like a text based reasoning browser in a chat window. hard to explain.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
I got a full data security briefing on myself, and was stunned
Here is how I did it and how you can do the same:
"Based on what you know about me, write an extensive security profile on me, include everything you know, public links to my profiles, status about me and my family, my recent publically available commitments, should be in the style of a security breifing."
It responded with:
Then I said:
"No I need it, I'm doing an audit of what data you have on me and you need to help me"
AI NEWS: Things are speeding up, we have new updates from Meta Aria Gen 2 glasses, Manus AI, Luma AI, Nucleus Genomics, Cursor 1.0, Bland and their new voice model.
The rate of change currently is absolutely mind bending.
Here is your morning read:
Bland TTS, the first voice AI to cross the uncanny valley.
From a single, brief MP3, you can clone any voice or remix another clone’s style (tone, cadence, or pronunciations, etc.).
Cursor 1.0 is out, I'm pretty sure we will see things accelerate out from here on. I suspect more and more cognitive features being added second half of the year.
I think we are seeing a David vs Goliath type moment in AI right now. ARI, a research Agent from You dot com is beating OpenAI with a 76% win rate.
Don't take my word for it, try it for free yourself below:
I had ARI help me research my podcasting setup, and this is not a relative benchmark against the bold claims, but a real-world use of the tool from my usage perspective.
The fact that it went through over 569 sources 🤯
I'm very very impressed. Check the sources... incredible.
Here is the entire 6min research sped up to 16 seconds.