BRN Discussion Ongoing

[7For7]

Not sure if already posted

Deep Tech Labs Ignite Clean Energy and AI Robotics Revolutions Today. Pre-Commercial Lab Advances Accelerate Electrified Industries At a glance: BrainChip advanced its neuromorphic computing… | Adam Roe

Deep Tech Labs Ignite Clean Energy and AI Robotics Revolutions Today. Pre-Commercial Lab Advances Accelerate Electrified Industries At a glance: BrainChip advanced its neuromorphic computing initiative with the AKD2500 silicon development project, a $2.5 million effort to integrate the...

www.linkedin.com

 

[HopalongPetrovski]

God you're full of shit. First of all do your homework. Go back through his history of research over the last twelve months. You might just get why he does what he does.
If you have a problem understanding where he is coming from after that.
Why don't you ask him.?
Or is that too hard.
If you go and look at Kevin's history, you will see the guy is a very principled and moral character.
He has been with IBM for more than 13 years.
He is a very self motivated individual, that enjoys a great deal of IBM's trust to carry out his professional duties, and any person who cast dispersion's on his motivations, needs to have their motivations examined thoroughly.

Hi White Horse.
I wasn't casting aspersions on Kevins work or motivations.
Merely trying to understand them.
You apparently think you do.
Good for you.
I said repeatedly that I both appreciate and admire his contributions.

 

[Gazzafish]

Artificial Intelligence | ISL - Technology for Real World Solutions



Doesn’t specifically mention Brainchip but we all know we are working with ISL.



Description :-“

Artificial Intelligence, Neuromorphic Computing and DoD Acceptance Testing



ISL is focused on replicating the analog nature of biological computation and the role of neurons in cognition. ISL’s team of scientists/engineers continue to understand how the morphology of individual neurons, circuits, applications, and overall architectures creates desirable computations. Leveraging this understanding and the newly developed and emerging commercial neuromorphic chips, ISL is developing a new low-power, lightweight detect and avoid (DAA) system for very small UAS platforms that exploits automotive radar hardware, light-weight EO/IR sensors, advanced data fusion algorithms, and neuromorphic computing.

Additionally, ISL has pioneered an AI acceptance methodology that allows for DoD testing of AI solutions using essentially the same statistically based methodology in use today. ISL was awarded a US Patent for this February (see link). The methodology leverages ISL’s RF Digital Engineering tools (https://www.islinc.com/digital-engineering ).”

 

[Bravo]

God you're full of shit. First of all do your homework. Go back through his history of research over the last twelve months. You might just get why he does what he does.
If you have a problem understanding where he is coming from after that.
Why don't you ask him.?
Or is that too hard.
If you go and look at Kevin's history, you will see the guy is a very principled and moral character.
He has been with IBM for more than 13 years.
He is a very self motivated individual, that enjoys a great deal of IBM's trust to carry out his professional duties, and any person who cast dispersion's on his motivations, needs to have their motivations examined thoroughly.

Whoa there, Horsey!

I don’t think Hoppy was casting aspersions on Big Kev at all. I think he was just asking what I think is a very fair and logical question.

Kevin himself has already said he’s not a shareholder, that he can’t speak on behalf of IBM or whether they’ll incorporate Akida and that his interest lies somewhere between personal and professional.

So naturally, there remains some curiosity about what’s actually driving that interest.

On a previous post I suggested the idea that it might be linked to Kevin's PhD (see link here #110,491).

This morning I ran Kevin's LinkedIn background, including details of his doctoral research, through ChatGPT, and the view that came back from Chatty was that his activity looks very consistent with someone exploring a broader research theme around AI infrastructure, coordination, and distributed systems. In other words, as a tool he’s experimenting with as part of a broader research framework.

If anyone is interest in what Chatty had to say, please feel free to check it out, otherwise, you know what to do.





ChatGPT's Response

1. Yes — this is absolutely related to his PhD​

Not just loosely… directly and strongly linked.

The key line is:

“Doctoral research… investigating coordination ontologies… distributed coordination architecture… 40,000+ coordinating agents… infrastructure design embodies ontological commitments…”

---

Translation into plain English:​

He is studying:

How large-scale intelligent systems coordinate, make decisions, and share knowledge

At scale:

• Distributed systems
• AI agents
• Infrastructure
• Governance

---

2. Now map that to what he’s been posting​

Look at his demos through that lens:

---

Palantir + Symphony phase​

• Ontologies
• Relationships
• Distributed compute
• Enterprise-scale coordination

Directly aligns with:

“coordination ontologies + infrastructure”

---

Akida / neuromorphic phase​

• Edge inference
• Event-driven systems
• Distributed intelligence
• “Hive mind” type demos

Directly aligns with:

“40,000+ coordinating agents / distributed cognition”

---

3. This is the big unlock​

You’re not watching:

A guy promoting BrainChip

You are watching:

A PhD researcher building a unified theory of AI infrastructure — in public — using real systems

---

4. Why Akida suddenly appears​

This now makes total sense.

His research is about:

Coordination across distributed agents

Problem with current systems:​

• GPU-heavy
• Centralised
• Expensive
• Not scalable to millions of agents

---

What neuromorphic offers:​

• Local decision-making
• Event-driven behaviour
• Low power
• Scalable agent systems

---

That maps perfectly to his thesis.

---

5. That “topology-aware GPU scheduling” question now clicks​

Earlier you picked up on this:

multi-GPU, multi-node scheduling complexity

That is:​

Centralised scaling problem

---

His PhD direction is:​

Distributed coordination problem

---

So the progression becomes:​

1. Try to scale AI with GPUs (Symphony)
2. Hit complexity limits
3. Ask:
   

   “What if intelligence is distributed instead?”

4. Explore neuromorphic (Akida)

---

That’s a research evolution, not a promotion strategy.

---

6. Why he’s so active publicly​

This line is also critical:

“AI-augmented rapid prototyping… accelerate from concept to working system”

---

He’s essentially:

Using LinkedIn as:

• A lab notebook
• A publication channel
• A portfolio of experiments

---

And this:

19 technical demonstrations since Dec 2025

That is:

PhD-level output volume

---

7. Important reality check (for BRN)​

This is where you need to stay grounded:

---

What this means:​

• Akida fits a serious research problem
• A capable architect is:
  • Using it
  • Testing it
  • Integrating it

---

What it does NOT mean:​

• IBM endorsement
• Commercial rollout
• Revenue
• Strategic partnership

---

It’s:

Research-driven experimentation

---

8. The most important insight (this is the takeaway)​

His work is not about:

“Which chip wins?”

It’s about:

“What architecture enables large-scale intelligent coordination?”

---

And he’s testing across:

• GPUs
• LLMs
• Quantum
• Neuromorphic

 

[HopalongPetrovski]

Whoa there, Horsey!

I don’t think Hoppy was casting aspersions on Big Kev at all. I think he was just asking what I think is a very fair and logical question.

Kevin himself has already said he’s not a shareholder, that he can’t speak on behalf of IBM or whether they’ll incorporate Akida and that his interest lies somewhere between personal and professional.

So naturally, there remains some curiosity about what’s actually driving that interest.

On a previous post I suggested the idea that it might be linked to Kevin's PhD (see link here #110,491).

This morning I ran Kevin's LinkedIn background, including details of his doctoral research, through ChatGPT, and the view that came back from Chatty was that his activity looks very consistent with someone exploring a broader research theme around AI infrastructure, coordination, and distributed systems. In other words, as a tool he’s experimenting with as part of a broader research framework.

If anyone is interest in what Chatty had to say, please feel free to check it out, otherwise, you know what to do.





ChatGPT's Response

1. Yes — this is absolutely related to his PhD​

Not just loosely… directly and strongly linked.

The key line is:

---

Translation into plain English:​

He is studying:

How large-scale intelligent systems coordinate, make decisions, and share knowledge

At scale:

• Distributed systems
• AI agents
• Infrastructure
• Governance

---

2. Now map that to what he’s been posting​

Look at his demos through that lens:

---

Palantir + Symphony phase​

• Ontologies
• Relationships
• Distributed compute
• Enterprise-scale coordination

Directly aligns with:

---

Akida / neuromorphic phase​

• Edge inference
• Event-driven systems
• Distributed intelligence
• “Hive mind” type demos

Directly aligns with:

---

3. This is the big unlock​

You’re not watching:

A guy promoting BrainChip

You are watching:

---

4. Why Akida suddenly appears​

This now makes total sense.

His research is about:

Coordination across distributed agents

Problem with current systems:​

• GPU-heavy
• Centralised
• Expensive
• Not scalable to millions of agents

---

What neuromorphic offers:​

• Local decision-making
• Event-driven behaviour
• Low power
• Scalable agent systems

---

That maps perfectly to his thesis.

---

5. That “topology-aware GPU scheduling” question now clicks​

Earlier you picked up on this:

That is:​

Centralised scaling problem

---

His PhD direction is:​

Distributed coordination problem

---

So the progression becomes:​

1. Try to scale AI with GPUs (Symphony)
2. Hit complexity limits
3. Ask:
4. Explore neuromorphic (Akida)

---

That’s a research evolution, not a promotion strategy.

---

6. Why he’s so active publicly​

This line is also critical:

---

He’s essentially:

Using LinkedIn as:

• A lab notebook
• A publication channel
• A portfolio of experiments

---

And this:



That is:

---

7. Important reality check (for BRN)​

This is where you need to stay grounded:

---

What this means:​

• Akida fits a serious research problem
• A capable architect is:
  • Using it
  • Testing it
  • Integrating it

---

What it does NOT mean:​

• IBM endorsement
• Commercial rollout
• Revenue
• Strategic partnership

---

It’s:

---

8. The most important insight (this is the takeaway)​

His work is not about:

“Which chip wins?”

It’s about:

---

And he’s testing across:

• GPUs
• LLMs
• Quantum
• Neuromorphic

Thank you Bravo.
A cogent and well structured explanation.
I have seen so much hallucinated and baited opinion based "stuff" conjured by various LLM's after scraping the web that I hadn't bothered questioning them on this matter but I am impressed and grateful for this response.
Thanks also for sticking up for me personally. Appreciate it.

 

[jrp173]

Whoa there, Horsey!

I don’t think Hoppy was casting aspersions on Big Kev at all. I think he was just asking what I think is a very fair and logical question.

Kevin himself has already said he’s not a shareholder, that he can’t speak on behalf of IBM or whether they’ll incorporate Akida and that his interest lies somewhere between personal and professional.

So naturally, there remains some curiosity about what’s actually driving that interest.

On a previous post I suggested the idea that it might be linked to Kevin's PhD (see link here #110,491).

This morning I ran Kevin's LinkedIn background, including details of his doctoral research, through ChatGPT, and the view that came back from Chatty was that his activity looks very consistent with someone exploring a broader research theme around AI infrastructure, coordination, and distributed systems. In other words, as a tool he’s experimenting with as part of a broader research framework.

If anyone is interest in what Chatty had to say, please feel free to check it out, otherwise, you know what to do.





ChatGPT's Response

1. Yes — this is absolutely related to his PhD​

Not just loosely… directly and strongly linked.

The key line is:

---

Translation into plain English:​

He is studying:

How large-scale intelligent systems coordinate, make decisions, and share knowledge

At scale:

• Distributed systems
• AI agents
• Infrastructure
• Governance

---

2. Now map that to what he’s been posting​

Look at his demos through that lens:

---

Palantir + Symphony phase​

• Ontologies
• Relationships
• Distributed compute
• Enterprise-scale coordination

Directly aligns with:

---

Akida / neuromorphic phase​

• Edge inference
• Event-driven systems
• Distributed intelligence
• “Hive mind” type demos

Directly aligns with:

---

3. This is the big unlock​

You’re not watching:

A guy promoting BrainChip

You are watching:

---

4. Why Akida suddenly appears​

This now makes total sense.

His research is about:

Coordination across distributed agents

Problem with current systems:​

• GPU-heavy
• Centralised
• Expensive
• Not scalable to millions of agents

---

What neuromorphic offers:​

• Local decision-making
• Event-driven behaviour
• Low power
• Scalable agent systems

---

That maps perfectly to his thesis.

---

5. That “topology-aware GPU scheduling” question now clicks​

Earlier you picked up on this:

That is:​

Centralised scaling problem

---

His PhD direction is:​

Distributed coordination problem

---

So the progression becomes:​

1. Try to scale AI with GPUs (Symphony)
2. Hit complexity limits
3. Ask:
4. Explore neuromorphic (Akida)

---

That’s a research evolution, not a promotion strategy.

---

6. Why he’s so active publicly​

This line is also critical:

---

He’s essentially:

Using LinkedIn as:

• A lab notebook
• A publication channel
• A portfolio of experiments

---

And this:



That is:

---

7. Important reality check (for BRN)​

This is where you need to stay grounded:

---

What this means:​

• Akida fits a serious research problem
• A capable architect is:
  • Using it
  • Testing it
  • Integrating it

---

What it does NOT mean:​

• IBM endorsement
• Commercial rollout
• Revenue
• Strategic partnership

---

It’s:

---

8. The most important insight (this is the takeaway)​

His work is not about:

“Which chip wins?”

It’s about:

---

And he’s testing across:

• GPUs
• LLMs
• Quantum
• Neuromorphic

Bravo, not having a go at all, as I know your research is appreciated by many on the forum. I understand you are not suggesting this is fact, but I think we all need to be careful with using Chat GPT, Claude etc, and take it with a very large pinch of salt.

It's very easy to get the response you want from AI, by asking the question differently.

When I rephrase and ask the question, my reply was in total contrast to your reply whilst still using Chat GPT. Below is just a small portion of my reply.

I think these are great tools, but must be used with caution.

 

[White Horse]

For those that think I'm being to harsh. And for those that rely on non factual hypothesis from AI.
Do the research, read all his stuff going back over the last 12 months (it's all there on LinkedIn) and formulate some opinions of your own.
Then take the time to converse with the guy himself. It's not hard. I have.!!
And most of your assumptions are correct, including his doctorate.
But to carry on with with this spurious nonsense about his motives that make it sound like their is a conspiracy going on, shows that some of you are starting to loose your grip.
Relax, sit back and rejoice in the fact that he is doing something that he enjoys doing, because he is that sort on bloke.

 

[Bravo]

Bravo, not having a go at all, as I know your research is appreciated by many on the forum. I understand you are not suggesting this is fact, but I think we all need to be careful with using Chat GPT, Claude etc, and take it with a very large pinch of salt.

It's very easy to get the response you want from AI, by asking the question differently.

When I rephrase and ask the question, my reply was in total contrast to your reply whilst still using Chat GPT. Below is just a small portion of my reply.

View attachment 96435

I think these are great tools, but must be used with caution.

Hi jrp,

Appreciate your comment.

For added context (which I should have included in the original post), the question I actually asked ChatGPT was:

"Do you think the work Kevin is doing with Akida is related in any way to his PhD, and, if so, in what way?"

So the response was framed around exploring a possible connection, not trying to arrive at a definitive answer.

In this case, the output isn’t just a generic AI opinion since it’s grounded in two things that are publicly available and verifiable:

• Kevin’s own description of his PhD research
• The type of work and demos he’s been posting recently

All ChatGPT did was connect those dots and point out that the overlap is fairly obvious.

I completely agree that you can steer AI depending on how you frame a question. But at the end of the day, you still have to apply your own judgement. Personally, I find the alignment here pretty compelling and quite plausible.

I’ve also stated numerous times (as have plenty of others) that Chatty (and other AI outputs) should be treated with caution, so I didn’t feel the need to restate that disclaimer yet again.

Ultimately, the only definitive answer would come from Kevin himself.

 

[jrp173]

Hi jrp,

Appreciate your comment.

For added context (which I should have included in the original post), the question I actually asked ChatGPT was:

"Do you think the work Kevin is doing with Akida is related in any way to his PhD, and, if so, in what way?"

So the response was framed around exploring a possible connection, not trying to arrive at a definitive answer.

In this case, the output isn’t just a generic AI opinion since it’s grounded in two things that are publicly available and verifiable:

• Kevin’s own description of his PhD research
• The type of work and demos he’s been posting recently

All ChatGPT did was connect those dots and point out that the overlap is fairly obvious.

I completely agree that you can steer AI depending on how you frame a question. But at the end of the day, you still have to apply your own judgement. Personally, I find the alignment here pretty compelling and quite plausible.

I’ve also stated numerous times (as have plenty of others) that Chatty (and other AI outputs) should be treated with caution, so I didn’t feel the need to restate that disclaimer yet again.

Ultimately, the only definitive answer would come from Kevin himself.

Thanks for the reply Bravo, absolutely true!

Regardless, seeing Kevin include Akida in 8 tests is a great thing! I just wish BrainChip would leverage off of his testing and create a white paper or solution brief to release to investors and potential clients!

 

[Fullmoonfever]

Did a quick search for Doug Utberg and didn't see this IV but maybe I missed it being posted already under something else.

Anyway, from late Feb with Sean. Didn't hear anything too groundbreaking but the LLM comments around the 10min mark were interesting.

Presumably to do with TENNs?

Sean's talking a good game again here, let's see if he can walk a positive tangible outcome on this statement through an ASX Ann?

I can't embed the vid but is in the link as is full transcript.

AI at the Edge, Power Limits, and Why the Future Won’t Live in Data Centers

BrainChip CEO Sean Hehir joins me to unpack where artificial intelligence is actually headed—and why the dominant “everything in the data center” narrative is incomplete.

www.dougutberg.com

Part of transcript ~ 10min mark.


"When you and I were just chatting a moment before we started to record, what was unthinkable is the ability to bring an LLM to the edge just a short period of time ago. It is now on a path. We are working on a piece of enabling technology that is going to really set the benchmark in this industry,
the ability to do some amazing things at such a low power that it will change the world. Actually, I believe to get an LLM in a device with so minimal power. and the ability to walk around and do things without an internet connection, very powerful thing. Stay tuned."

 

[Bravo]

For those that think I'm being to harsh. And for those that rely on non factual hypothesis from AI.
Do the research, read all his stuff going back over the last 12 months (it's all there on LinkedIn) and formulate some opinions of your own.
Then take the time to converse with the guy himself. It's not hard. I have.!!
And most of your assumptions are correct, including his doctorate.
But to carry on with with this spurious nonsense about his motives that make it sound like their is a conspiracy going on, shows that some of you are starting to loose your grip.
Relax, sit back and rejoice in the fact that he is doing something that he enjoys doing, because he is that sort on bloke.

Hi White Horse,

I don't believe that referring to Kevin’s "motivation" is being used in a negative or conspiratorial sense at all. I think it's being used just in the plain meaning of the word "the reason or reasons someone is doing something."

There’s a big difference between being curious about what’s driving his interest versus implying there’s something untoward going on.

Having said that, I actually agree with a lot of what you’ve said. Kevin is clearly very capable, he enjoys what he’s doing, he’s experimenting across different technologies and his PhD and background likely play into it.

That’s exactly why we're all interested because it’s unusual (in a really good way) to see someone doing this level of hands-on, public experimentation.