MindReader v1
Read minds (simulated fMRI data, channeled to neuro-metrics)
Start new thread

MindReader v1 - Read minds (simulated fMRI data, channeled to neuro-metrics)

by•
How do you feel? It is the oldest question in art and the newest one we can answer in technology. MindReader takes your content and simulates, region by region, how a brain responds to it. Completely Open Source - we encourage you to tinker. Exploring sales evals, neural evals for datasets and other esoteric product experiments w/ madhat founders. MindReader is built on Meta FAIR's TRIBE v2 + 35yrs of neuro research. Inviting collab from the academics et all.

Add a comment

Replies

Best
Maker
📌
Hello PH! Introduction: MindReader simulates, second by second how a brain responds to any content Explanation: It feeds TRIBEv2 data into an insights miner that is run by a neuro-analyst agent. 7-dimensions are explored. Attention (for eg) is based on Dr. Falks' research work etc. Inspiration: How do you feel? EQ in AI Evolution: initalyy started as brainDiff (focused on A vs B results for each 'similar content' to battle absence of baselines) - ended up normalizing output scores using basic stats. CTA: Run you latest social media post through the platform - (self-host available)

the ositioning is bold, but also risky. When terms like “read minds” are used, expectations can easily go far beyond what simulated neuro-data can realistically provide.

 A suggestion from my side would be to include benchmark comparisons against more standard UX testing tools so people understand where this fits in the stack.

Maker

 we resonate! Hence we also decided to open-source the product and research.

MindReader predicts what an average brain response would look like - specifically the blood flow. details out everything that goes behind making Mindreader's science backed magic.

One concern I have is overinterpretation. users might treat simulated neural outputs as scientific truth, so clear framing and limitations will be important.

Maker

 we completely agree! Which is why we chose to build in a completely open source manner. We want to strengthen these metrics, test them rigorously before pushing them to consumer products.

Clear communication and community accountability is a core part of our DNA. Appreciate the flag.

Bold vision here. The open-source angle makes it even more exciting for people who love tinkering and experimenting.

Maker

   Thank you for checking out the product! We believe that the trust surface here has to be large.

The only way to make people believe that we can 'read minds' is by keeping our methodology and research out in the open. Looking forward to making the product even more robust.

Simulating how a brain reacts to content is a fascinating concept, and love that it's open source. How accurate are the neuro-metrics compared to real fMRI studies?

Maker

good question, and the honest answer is it's a prediction, not a measurement. TRIBEv2 doesn't read a brain. It predicts the fMRI response an average brain would produce, trained on ~1,000 hrs of real scans across 720 subjects. Meta reports 2–3x better accuracy than prior encoding models, and zero-shot correlation around 0.4 on subjects it's never seen. So: good, not gospel.

What that means in practice one should trust it for relative signal (where attention holds vs. drops inside one piece of content) far more than absolute numbers.

The 7 signals sit as an interpretive layer I built on top of the voxel predictions, mapped to published region → function research. That layer carries its own assumptions, which is exactly why it's open source - so peers can audit / tweak it.

Hi, Tried the product at the trial setup page and honestly the experience felt like stepping into a neuroscience lab 😄 The visualizations are fascinating and definitely spark curiosity. At the same time, I found myself wondering how much of the report reflects real cognitive signals versus an interpretive model. Either way, it's a very memorable experience and a fresh way to think about message analysis.

Maker

really appreciate the note. the UI/UX is us leaning into the sci-fi world on purpose- the product's inspired by a lot of sci-fi stories we love.

on your actual question, real cognitive signal vs interpretive model- it's both, and worth separating.

  • the brain map is a prediction from TRIBEv2, which is trained on ~1,000 hrs of real fMRI, so the regional activity you're seeing is grounded in real scan data, not invented.

  • the interpretive part is the layer on top: the 7 signals and scores like Personal Resonance 0.85. that's us mapping predicted activity in known regions to named functions, based on published research, then normalizing the output. so the activity is modeled from real brains; the labels are our reading of it.

    that's exactly the layer we open-sourced- it's the part worth poking holes in.

PS: actually has a '42' tattoo; v. devoted sci-fi fan

Maker

Hey Product Hunt community! 👋

Thrilled to see this first launch from the collective hitting the top 10 (#9 right now! 🚀).

MindReader V1 is the result of deep research and countless hours collaborating with sales teams to solve real workflow bottlenecks. The best part? It’s already driving impact. We're currently being integrated into the evaluation pipelines of a marketing team and a YC-backed sales AI agent.

Huge shoutout to for building something users are clearly loving. As a co-maker, I’d love to get your thoughts - where would you like to use it in your product or agent pipeline?

Maker

 thank you for getting this mad-lab going. I'm excited to contribute to more open source stuff at .

Also again shoutout to the village that supported MindReader on our journey. We are keenly looking to working with academic folks, voice and sales founders / operators - actually all curious folks are welcome.

Open areas of conversation / areas we are keen to explore further:

  • neural-tags for dataset (voice in particular)

  • evals

  • content / sales / coaching

  • d: <enter your answer>

Very interesting, and great that it's open source. But I'm not sure I understand it correctly. So the goal is to determine how a demographic will respond to certain sales call scripts or ad creatives?

Maker

 the surface area for the product is much wider.

  • it is useful in anything that benefits from a proxy of human reaction to it.

  • we have already discussed sales calls coaching as a use case; content / marketing / ads would work in a similar way

  • some other use cases

    • neural tags for datasets (many YC audio start-ups (like usepanels.com) are selling expressive data, they can attach this as an objective measure of emotion). (would love for to weigh in)

    • call centres for distress calls can use it to train their agents even better

there are also darker use cases: like reverse engineering a "calm video" to hit certain neural-metrics - which is why we have chosen to stay completely open source and are building on the frontier

This is weird in the best Product Hunt way. Simulated mind reading for UX feels half research lab, half startup fever dream.

This is what engineers must feel like when I show them my code. Essentially, you’ve created a visualization based on averaged fMRI data to help people conceptualize what brain areas are related to certain tasks and domains?
Maker

 so the platform runs your content second by second and pulls the top 3 moments where a signal spikes. so instead of "here's the gut reaction region," you get a snippet like this:


Open areas of conversation / areas we are keen to explore further:

  • neural-tags for dataset (voice in particular)

  • evals

  • content / sales / coaching

  • d: <enter your answer>

12
Next