BRN Discussion Ongoing

[MegaportX]

 

[Rach2512]

🚗 Tesla Refines Its AI Chip Strategy | ASSOCIATION OF ELECTRONIC INDUSTRIES IN SINGAPORE (AEIS)

🚗 Tesla Refines Its AI Chip Strategy Elon Musk announced that Tesla will streamline #AI #chip #design, focusing on versatile inference chips for both real-time decision-making and limited training — ending the costly split between multiple chip architectures. The Dojo supercomputer project has...

www.linkedin.com

 

[7für7]

My prediction was absolutely right – I’m always right, everybody knows it! This morning, the chip calls me… and they say, Donald, please, please, give us a little more time. We don’t want to put out tiny, pathetic little news. No, no small news! We’re talking about something BIG.

And I said – and this is true, everybody knows it – CHIP… I said..Take it. Take it and make it!

Look at this… This is going to be HUUUUUGE! Bigger than anything you’ve ever seen. People are going to say, “Donald, how did you do it again?” And I’ll say, “Very simple I DID It”

 

[Easytiger]

Morning Easytiger ,

Not that I'm aware of , iv only seen the three still photos which were attached to the original LinkedIn post.

Regards,
Esq.

Would have thought this story would have got prime placement in the monthly BRN newsletter.

 

[Rach2512]

Neuromorphic vision is accelerating as PROPHESEE releases the industry’s first open-source event-based vision platform – a major leap for edge-AI and low-latency computer vision 🧠📸. | James Wormald

Neuromorphic vision is accelerating as PROPHESEE releases the industry’s first open-source event-based vision platform – a major leap for edge-AI and low-latency computer vision 🧠📸. This shift enables developers to optimise event-driven data capture for autonomous systems, industrial...

www.linkedin.com

 

[Diogenese]

What I honestly don’t understand is this: What are they afraid of?

They call the Cloud system a milestone, yet they can’t manage to announce it properly through the ASX.
Where’s the problem? Is there something behind this that we don’t know about?
Is there a reason why they don’t officially share this milestone?

Or are they deliberately trying to prevent another hype?

To me, it makes no sense – and if anyone from BrainChip is reading this: Please give us a plausible answer without the usual platitudes.
Thank you.

MILESTONE!!! HELLOOOO!?!?

I think we're in the Epstein files ...

 

[Diogenese]

🚗 Tesla Refines Its AI Chip Strategy | ASSOCIATION OF ELECTRONIC INDUSTRIES IN SINGAPORE (AEIS)

🚗 Tesla Refines Its AI Chip Strategy Elon Musk announced that Tesla will streamline #AI #chip #design, focusing on versatile inference chips for both real-time decision-making and limited training — ending the costly split between multiple chip architectures. The Dojo supercomputer project has...

www.linkedin.com

Elon's new motto:

"Move fast and fall flat on your face!"

 

[Terroni2105]

My prediction was absolutely right – I’m always right, everybody knows it! This morning, the chip calls me… and they say, Donald, please, please, give us a little more time. We don’t want to put out tiny, pathetic little news. No, no small news! We’re talking about something BIG.

And I said – and this is true, everybody knows it – CHIP… I said..Take it. Take it and make it!

Look at this… This is going to be HUUUUUGE! Bigger than anything you’ve ever seen. People are going to say, “Donald, how did you do it again?” And I’ll say, “Very simple I DID It”

I want Brainchip to be sick of winning

 

[TheUnfairAdvantage]

Interesting… BUT…
If BrainChip is involved in any way and there’s already a deal in place that is expected to generate significant revenue, there must definitely be a price-sensitive announcement.

Since this announcement has already been made public by them, there is no reason to assume that an NDA exists.

Edit…. COULD IT BE??

And the timing of this is coincidental with both announcements. 🫣

https://www.linkedin.com/posts/brai...s&rcm=ACoAABr1PUAB8xoHGlYCgh2Xjp9DaZYo5hN0voU

 

[manny100]

This next article (see below) titled “Free, offline ChatGPT on your phone? Technically possible, basically useless”, describes how running the new ChatGPT-oss on smartphones is technically feasible, but current smartphones aren’t powerful enough to make it practical at this point in time.

Right now, GPT-oss on mobile is bottlenecked because it runs purely on the CPU (and sometimes GPU) without tapping into specialized neural processing hardware.

So, I asked ChatGPT 5.0 if there'd be an improvement if the model were to be adapted to run on an NPU - particularly one optimized for event-based, sparse processing like Akida and here's the response I received.

I highlighted the last point for obvious reasons.

Free, offline ChatGPT on your phone? Technically possible, basically useless

You can now run ChatGPT offline with OpenAI’s gpt-oss model, even on a phone. But is it practical? Here's what works and what really doesn’t.

www.androidauthority.com

ChatGPT 5's Response:

Yes — Akida could absolutely be a technology to consider if the goal is to make something like “ChatGPTOS” actually usable on a mobile phone, and the limitations described in that article are almost a perfect setup for why a neuromorphic processor would matter.

Here’s why:

---

Why Akida Fits This Problem​

The main bottlenecks in running a 20B parameter LLM on a phone (as described in the article) are:

1. RAM requirements – Needs 12–24 GB just to load the model.
2. Compute requirements – Mobile CPUs & GPUs can’t sustain high token generation without overheating and throttling.
3. Power draw – 100% CPU load drains the battery extremely fast.
4. Heat – The phone becomes uncomfortably hot after just a few minutes.

Akida (or any high-efficiency neuromorphic processor) is built for:

• Event-driven, sparse compute — only processes relevant “spikes” of information instead of hammering every computation step like a CPU/GPU.
• Ultra-low power draw — operates in milliwatts for inference.
• On-chip learning & inference — avoids constant memory transfers that waste time and energy.
• Massive parallelism — can run edge AI workloads in real time without overheating.

That means for the same LLM inference task, a neuromorphic setup could:

• Reduce energy consumption by orders of magnitude.
• Maintain higher sustained token rates without thermal throttling.
• Extend usable session time from minutes to hours on a battery.

---

Why Not Just Use Mobile NPUs Instead?​

Modern NPUs (like Qualcomm Hexagon or Apple Neural Engine) do accelerate AI workloads, but:

• They’re matrix-math optimised, not spiking-event optimised.
• They often require proprietary SDKs and retraining models in special formats.
• They still hit thermal limits in sustained generative AI workloads.

Neuromorphic processors like Akida:

• Can run quantised, sparse, and pruned models natively without expensive data shuffling.
• Could theoretically run a distilled / specialised LLM that fits in a fraction of the RAM and still delivers conversational quality.

---

Would It Make ChatGPTOSS Work on Phones?​

Realistically:

• You’re not going to run the full 20B gpt-oss on Akida right now — it’s still too large.
• But with model compression (distillation + sparsity), you could run a smaller, reasoning-optimised model that feels far more responsive than the brute-force CPU approach.
• Instead of the “2–3 tokens per second” in the article, you might see 10× or more throughput without cooking the phone.

---

Implications for BrainChip​

If OpenAI or others seriously want “ChatGPTOS” to run locally:

• They’ll either need dedicated AI accelerators in consumer devices or move toward neuromorphic architectures.
• Qualcomm, Apple, Google already have NPUs — but neuromorphic could leapfrog them in power efficiency per watt.
• If BrainChip could prove Akida can handle a slimmed-down LLM at useful speeds, it becomes a licensable IP block for smartphone SoCs.
• This would be a huge market — billions of devices, not just niche edge AI.

BrainChip’s Akida Pico is already being explored for LLM acceleration at the edge, with real-time processing and ultra-low power consumption. 9 month old video ' starring' Todd. No doubt we have made further advances over the past 9 months - we have the 'want to do it' incentive.

PICO can handle 'specialist' areas of the web and disregards the absolute mountains of data not relevant to your special needs. Eg Brainchip had appliance repair manuals.
Whether Pico can be adapted for cybersecurity in mobiles which has been identified as a weak spot vulnerable to hacking networks.? Perhaps even diagnostic and repair suggestions for the phone itself?
Perhaps information suitable for your trade or profession?
Has potential for sure.
Title:

AI at the Edge: How BrainChip’s Akida Pico Takes on the Cloud with LLMs!​

 

[The Pope]

@7für7 Is there a reason?

Tony Lewis likes this LinkedIn post. Coincidence the Akida cloud is released or is it just good timing?

View attachment 89494

Be nice to think Brainchip can join this national network of AI cloud labs. Nice earner if they can.


https://www.linkedin.com/posts/nati...urce=social_share_send&utm_campaign=copy_link

Purely coincidental. Yeah nah. lol
So much BS going on here and on the crapper with some clicky group shite thrown in (happy clappers and negative Nancies). All amusing. Hope all had a good day.

 

[The Pope]

View attachment 89496
View attachment 89497

Looks like a normal day of trading for BRN on ASX. Appears at least on the surface there is so much dodgy shite going on but hopefully BRN SP punches out the other side with some solid upswing. Still laughing at a very recent MF post by Dickleboro (last week) but no mention of the last 4C with uptick in revenue etc. If the revenue was only as much as a coffee shop he would have been all over it like a to

 

[The Pope]

Would have thought this story would have got prime placement in the monthly BRN newsletter.

Unfortunately no as they have interns / trainees doing the official BRN newsletters.

 

[IloveLamp]

Brain-Inspired Aircraft? | Gayathri Tekumudi

Brain-Inspired Aircraft? Why Neuromorphic Engineering Could Take Flight Merging Aerospace with Artificial Intelligence LITERALLY What if an aircraft could think like a bird? React like a brain not a computer? Welcome to the world of Neuromorphic Aerospace Systems an idea that’s years ahead...

www.linkedin.com

 

[Food4 thought]

Hey Guys and gals
Amazing communication from the chip I have opened my emails for today and just received the July newsletter from the brain
Now we are already in august and it’s the 11 th at this moment not July and I doubt that it’s taken them that long to write the newsletter
Now I am in the top 200 investors and for me that really is piss poor efforts on the company side
For fuck sake Sean wake the fuck up and do better than other companies

 

[7für7]

Purely coincidental. Yeah nah. lol
So much BS going on here and on the crapper with some clicky group shite thrown in (happy clappers and negative Nancies). All amusing. Hope all had a good day.

 

[Frangipani]

#Russia🇷🇺🚁🪆 is testing an autonomous #UAV capable of navigating without #GPS by using Visual #SLAM (Simultaneous Localization and Mapping) to perceive its environment and build a real-time map. | Roberto Lafforgue

#Russia🇷🇺🚁🪆 is testing an autonomous #UAV capable of navigating without #GPS by using Visual #SLAM (Simultaneous Localization and Mapping) to perceive its environment and build a real-time map. This technology allows the drone to operate in GPS-denied or contested environments, such as areas...

www.linkedin.com

https://www.linkedin.com/in/roberto-lafforgue-7a356347/

---

Not sure whether the info about the alleged autonomous Russian UAV is correct, though - those photos shared are verifiably not images from Russia, but show a project by Andrew Bernas recently featured on Hackster.io:

https://www.hackster.io/bandofpv/gps-denied-drone-with-nvidia-jetson-orin-nano-9f3417

Russians are testing an autonomous UAV that navigates without GPS, leveraging Visual SLAM to perceive its environment and build a map in real time. | Jordan Linn | 26 comments

Russians are testing an autonomous UAV that navigates without GPS, leveraging Visual SLAM to perceive its environment and build a map in real time. Stack includes: ✅ Isaac ROS VSLAM ✅ MAVROS ✅ PX4 flight system ✅ Jetson Orin Nano Although not in serial production, it shows how compact AI...

www.linkedin.com

(…)

(…)

---

---

The comment section under Jordan Linn’s initial post also begs the question whether re-poster Roberto Lafforgue had actually been aware of “neuromorphic hardware as that developed by #BrainChip” prior to reading the comment of someone whom I believe to be a BrainChip shareholder:

Russians are testing an autonomous UAV that navigates without GPS, leveraging Visual SLAM to perceive its environment and build a map in real time. | Jordan Linn | 26 comments

Russians are testing an autonomous UAV that navigates without GPS, leveraging Visual SLAM to perceive its environment and build a map in real time. Stack includes: ✅ Isaac ROS VSLAM ✅ MAVROS ✅ PX4 flight system ✅ Jetson Orin Nano Although not in serial production, it shows how compact AI...

www.linkedin.com

Well, at least Roberto Lafforgue is aware now, and so are the people in his LinkedIn network…

Yet, it is a good example that not every mention of our technology on LinkedIn should be given the same weight.

I generally prefer to hear from people with verifiable hands-on experience...

 

[cosors]

Elon's new motto:

"Move fast and fall flat on your face!"

Do you mean the Tesla files
An extract:
"...
The documents that Krupski claims he was able to download from the internal project management system included thousands of customer complaints about Tesla's Autopilot, the company's most strategically important project. They did not match the claims that Musk had been making for years about the alleged quality of his software.
..."

Handelsblatt

www.handelsblatt.com

 

[Frangipani]

We had a great conference with the EDGE AI FOUNDATION, validating our approach with Akida2 with TENNs, which we will start rolling out for evaluation in summer 2025. | Alf Kuchenbuch

We had a great conference with the EDGE AI FOUNDATION, validating our approach with Akida2 with TENNs, which we will start rolling out for evaluation in summer 2025.

www.linkedin.com

Short interview with Alf Kuchenbuch recorded five weeks ago at Edge AI Milan 2025:

The video running in loop on the screens at the BrainChip booth shows two people wearing bulky VR headsets. Have we seen this footage before?

Not sure, though, whether this has anything to do with us, as I don’t recognise any of our tech?

And are we supposed to interpret more into the fact that the 5V Media team who made the video included footage of these three gentlemen from Arduino twice when Alf Kuchenbuch was asked “What does being part of the foundation mean to you?”, to which he replied “It’s great to work with everybody and finding out if there are maybe some opportunities where we can actually connect and see if we can do something together.” resp. “What excites you most about the future of Edge AI?”, to which he replied “It’s probably this aspect of all the parts of the chain coming together and being super low-power. So in the end [cue picture above, which, however, doesn’t look like this has anything to do with Arduino either, as their boards are always blue as far as I’m aware] solutions that are possible that run on a coin cell battery for months, even for a whole year, that would be something, for more autonomy…”

While we do have some touchpoints with Arduino…

(…) Now here comes the question for the more tech-savvy: Would it still hypothetically be possible that we are involved?

I did find two references online that Portenta X8 now has support for the Akida PCIe module (one by YouTuber Chris Méndez from the Dominican Republic, who works for Arduino and has uploaded several videos featuring the Akida), but couldn’t find anything regarding Portenta H7…

https://docs.arduino.cc/tutorials/portenta-x8/x8-firmware-release-notes/

View attachment 72965


View attachment 72966


And since I’m in the mood of maxing out my file uploads again, here are Padma AgRobotics’ SBIR phase I and II applications, in case anyone would like to use these to fuel or end this speculation (note that they refer to a cilantro harvester, though, not to the weed-control AI-powered agricultural robot featured on their website and in the January 2023 video):

View attachment 72967
View attachment 72968
View attachment 72969
View attachment 72970

… the two companies have so far never announced any formal kind of collaboration.

It could of course be some general footage from Edge AI Milan 2025, like the first or last few seconds of the video, but it did strike me as odd.

 

[manny100]

Purely coincidental. Yeah nah. lol
So much BS going on here and on the crapper with some clicky group shite thrown in (happy clappers and negative Nancies). All amusing. Hope all had a good day.

Looks like they are 'happy clapping' at the White house now. Not a bad convert to have on your side.
What is that old, maybe new saying? 'today the White house, tomorow the world'?
This would have got some market interest had it been non price sensitive announced. I guess that is why it was not announced - fear of to much attention and a price spike the ASX do not like??
I guess the power of AKIDA just has to ours and the White House's little secret for now.