BRN Discussion Ongoing

[Diogenese]

Some very big statements from Sean .

13 minute mark & onwards



View attachment 93392

My shorthand is non-existent, but I'll try to verbal Sean:

13:15 - "We have technology that can support that (edge AI). We have a set of models we are going to commercialize in subsequent quarters

We have a set of models that can support Generative AI

Stay tuned

Later this year/early next year - functionality"

 

[Jacob Kiraz]

My shorthand is non-existent, but I'll try to verbal Sean:

13:15 - "We have technology that can support that (edge AI). We have a set of models we are going to commercialize in subsequent quarters

We have a set of models that can support Generative AI

Stay tuned

Later this year/early next year - functionality"

Hopefully the next few announcements that were mentioned by Sean can rock more than knocking the top off a Custard tart

 

[TheDrooben]

My shorthand is non-existent, but I'll try to verbal Sean:

13:15 - "We have technology that can support that (edge AI). We have a set of models we are going to commercialize in subsequent quarters

We have a set of models that can support Generative AI

Stay tuned

Later this year/early next year - functionality"

From approx 14:25......

"There's some very interesting things that are coming through. I would say simply, stay tuned to us, and watch what we are going to announce later this year. I think you will be amazed by the functionality that we are going to be talking about"......"Later this year/early next year there's a lot of things we are going to be announcing"

 

[smoothsailing18]

Could someone with acces/ member to crapper, post the below here please

Doz
4,954 Posts.
4820

29/11/25

14:08

Post #: 81860270

 

[Fiendish]

 

[smoothsailing18]

<iframe src="https://hotcrapper.com.au/threads/2025-brainchip-discussion.8349709/?post_id=81860270&embed=1

" width="500" height="893" style="border:1px solid #DADADA;overflow:hidden" scrolling="no" frameborder="0" allowTransparency="true" allow="encrypted-media"></iframe>

That's got a problem as well

 

[smoothsailing18]

Manny100

1. Wow, this is huge. Great research Doz. Another 'notch' on the Brainchip belt.
   Megachips Licence November 2021.
   Acumino formed in 2023
   In March 2025 Megachips partnered with Acumino in March 2025.
   Acumino and Megachips jointly established Japan’s first demonstration and test environment for AI-powered robot workers at Megachips’ site and it allows customers to see the robots in action.
   Megachips has sole distribution rights in Japan where there are acute labor shortages.
   Loihi and IBM True North have NO known association with megachips and are not yet commercial.
   Megachips has invested $ into the company but no details are available.
   Acumino is still pre‑revenue, but strategically positioned with megachips to move from demonstrations into commercial deployments.
   Acumino currently has offices in the U.S., EU, and NZ suggest Acumino is preparing for broader commercialisation once Japan proves viability.
   No doubt another reason for Sean's 'watch us now' statement

 

[Fiendish]

cumino AI Assistant
Ask me about our AI-powered robot workers

Hello! I'm your Acumino AI assistant. I can help you learn about our AI-powered robot workers, automation solutions, and Industry 5.0 services. What would you like to know?

17:35:41
Are your robots capable of one shot learning

17:36:13
Acumino's robots are designed with advanced AI capabilities that enable them to perform highly dexterous tasks and adapt to complex environments. While specific details about one-shot learning are not explicitly mentioned in our publicly available information, our AI systems are built to be scalable and reliable, leveraging the most accurate data of robot interactions. This allows for fast and cost-efficient deployment, which may include elements of advanced learning techniques.

If you have further questions about our AI-powered robot workers or specific capabilities, feel free to ask!

17:36:17
Can acumino robots learn from mistakes without cloud connections

17:37:40
Acumino's AI-powered robots are designed to operate with a high level of autonomy, which includes the ability to adapt and learn from interactions in their environment. While specific details about offline learning and cloud connectivity are not provided in our available resources, the emphasis is on creating scalable, reliable, and cost-efficient solutions.

Our robots utilize a combination of advanced AI and data from wearable collection systems to enhance their dexterous capabilities. This approach enables them to perform complex tasks and adapt to changes in their environment, potentially including learning from mistakes.

 

[manny100]

cumino AI Assistant
Ask me about our AI-powered robot workers

Hello! I'm your Acumino AI assistant. I can help you learn about our AI-powered robot workers, automation solutions, and Industry 5.0 services. What would you like to know?

17:35:41
Are your robots capable of one shot learning

17:36:13
Acumino's robots are designed with advanced AI capabilities that enable them to perform highly dexterous tasks and adapt to complex environments. While specific details about one-shot learning are not explicitly mentioned in our publicly available information, our AI systems are built to be scalable and reliable, leveraging the most accurate data of robot interactions. This allows for fast and cost-efficient deployment, which may include elements of advanced learning techniques.

If you have further questions about our AI-powered robot workers or specific capabilities, feel free to ask!

17:36:17
Can acumino robots learn from mistakes without cloud connections

17:37:40
Acumino's AI-powered robots are designed to operate with a high level of autonomy, which includes the ability to adapt and learn from interactions in their environment. While specific details about offline learning and cloud connectivity are not provided in our available resources, the emphasis is on creating scalable, reliable, and cost-efficient solutions.

Our robots utilize a combination of advanced AI and data from wearable collection systems to enhance their dexterous capabilities. This approach enables them to perform complex tasks and adapt to changes in their environment, potentially including learning from mistakes.

" Acumino's AI-powered robots are designed to operate with a high level of autonomy, which includes the ability to adapt and learn from interactions in their environment."
Says it all.
Pretrained robots = static intelligence → good at repeating known tasks.
Adaptive robots = dynamic intelligence → capable of learning new tasks on the fly.
Only chips with on chip learning can adapt and learn from interactions in their environment.
Whilst AKIDA is the 'be all, end all' for us for Acumino it is only one piece (albeit important) of an extremely complex robot. They would probably focus on their sophisticated software.

 

[Doz]

The post looked something like this on HC and I asked if anyone knows what product in the MegaChip’s catalogue is capable of one shot learning ?

And of course we all remember what example Tony gave when showing off the new AKD 2.0 FPGA ,,,

 

[manny100]

The post looked something like this on HC and I asked if anyone knows what product in the MegaChip’s catalogue is capable of one shot learning ?

View attachment 93396


View attachment 93397
View attachment 93398



View attachment 93402


View attachment 93400


And of course we all remember what example Tony gave when showing off the new AKD 2.0 FPGA ,,,




View attachment 93401

That was great research Doz, cheers

 

[FJ-215]

The post looked something like this on HC and I asked if anyone knows what product in the MegaChip’s catalogue is capable of one shot learning ?

View attachment 93396


View attachment 93397
View attachment 93398



View attachment 93402


View attachment 93400


And of course we all remember what example Tony gave when showing off the new AKD 2.0 FPGA ,,,




View attachment 93401

License agreement please!!!!!!!!

 

[Doz]

I wonder if MegaChip’s had a dabble into the Brainchip placement @ $0.175 ?

Buy , Buy , Buy ,,,,

Sell , Sell , Sell ,,,,

Seriously acting more like day traders than a well respected tech company !


Although , not a bad investment return on SiTime , I might start following them ….

.

 

[Jacob Kiraz]

License agreement please!!!!!!!!

Ive got a question,
If Mr Heir is stating Watch us Now and there be announcements before years end, why isnt the shareprice going up, Surely people are in the know ?
Why isnt the shareprice going up

 

[Diogenese]

The post looked something like this on HC and I asked if anyone knows what product in the MegaChip’s catalogue is capable of one shot learning ?

View attachment 93396


View attachment 93397
View attachment 93398



View attachment 93402


View attachment 93400


And of course we all remember what example Tony gave when showing off the new AKD 2.0 FPGA ,,,




View attachment 93401

Hi Doz,

Hoping that your dot joining is correct. The link to Tony carries a lot of weight, but, while the auguries are good, even the Delphic oracle was famously "open to interpretation",

Megachips have their in-house DRP (Dynamically Reprogrammable Processor), which they announced would be used for the heavy lifting while Akida swept the floor.

More recently, Megachips "discovered" N-of-M coding, which is a sparsity tool.

This is a recent Acumino patent application:

US2024408757A1 HUMAN-IN-LOOP ROBOT TRAINING AND TESTING SYSTEM WITH GENERATIVE ARTIFICIAL INTELLIGENCE (AI) 20230609

A robot teaching and testing system and method that performs human-operated robot tasks according to instructions generated from generative AI models. The process starts with a user prompt and combines the user prompt with predefined prompt templates to generate well-formatted text prompts. Generative AI models take the text prompts and convert them into high-level instructions or control codes that can be deployed on a robot. The high-level instructions are then converted into human-operated robot tasks for a human data collector using a mixed reality (MR) device. The human data collector will attempt to follow the instructions to complete the human-operated robot tasks and may overwrite the suggested instructions by performing a different action, demonstrate a task without instructions, or leave feedback or comments regarding the tasks. Feedback data will be captured and saved for improving the robot system.

Clearly, Megachips would be providing any NN SoC knowhow.

On the other hand Akida GenAI would be useful for such an application.

 

[manny100]

The post looked something like this on HC and I asked if anyone knows what product in the MegaChip’s catalogue is capable of one shot learning ?

View attachment 93396


View attachment 93397
View attachment 93398



View attachment 93402


View attachment 93400


And of course we all remember what example Tony gave when showing off the new AKD 2.0 FPGA ,,,




View attachment 93401

Worth highlighting from your post.
" Acumino’s technology is currently in trials with a major German automaker, a large Japanese marine engine producer, and other international manufacturers. “Our system runs on standard robots and hardware and can be deployed on-site with strong data privacy and local control.”"

 

[TheFunkMachine]

For anyone interested here is a summary put together through ChatGPT of every Defence engagements Brain chip has had over the past 5 years. Please let me know if you notice it is missing something. This space is heating up IMO and this only public knowledge. In defence particularly there would be strict NDAs on anything of national interest.

• Information Systems Laboratories (ISL) & U.S. Air Force Research Laboratory (AFRL) – 9 January 2022
  BrainChip announced that ISL was developing an AI-based radar research solution for the U.S. Air Force Research Laboratory using the Akida processor, under an early-access program. This placed Akida into defence radar R&D for USAF via ISL’s AFRL project.
• Blue Ridge Envisioneering (BRE – U.S. defence & intelligence engineering firm) – 10 April 2023
  BrainChip and Blue Ridge Envisioneering, an engineering specialist serving defence and intelligence communities, announced a collaboration to integrate Akida into next-generation tactical edge devices. BRE uses Akida in designs for tactical devices contracted by defence and intelligence agencies, focused on low-power, sensor-driven decision support at the edge.
• U.S. Air Force Research Laboratory (AFRL) – direct radar contract – 9 December 2024 (ASX notice 10 December 2024; media 10–11 December 2024)
  BrainChip announced it had been awarded a development contract worth ~US$1.8m (≈US$2.7m total program value reported in media) from the U.S. Air Force Research Laboratory under the SBIR program. The work is to develop neuromorphic radar signal-processing technologies on Akida, specifically micro-Doppler-based radar signal analysis for USAF missions.
• Bascom Hunter (U.S. defence contractor) – late December 2024 (reported in 31 January / 28 January 2025 filings & media)
  BrainChip signed a US$100,000 contract with U.S. defence contractor Bascom Hunter for the sale and support of AKD1500 chips. The chips are being evaluated for low-SWaP (size, weight, power) defence and intelligence applications, with Bascom integrating third-party tech such as Akida into defence platforms (e.g. Navy SBIR-related work).
• Information Systems Laboratories (ISL) – expanded radar partnership (military & aerospace) – 31 March 2025 / 7 April 2025
  BrainChip and ISL announced a deeper partnership to jointly promote and provide AI-based radar research solutions using Akida. The platforms span drones up to large radar systems for military and aerospace customers, consolidating Akida’s role in defence radar intelligence at the edge.
• Raytheon (RTX) & U.S. Air Force Research Laboratory – AFRL neuromorphic radar project – 2 April 2025 (press release; related coverage 1–14 April 2025)
  BrainChip announced it is partnering with Raytheon (an RTX defence prime) to execute the previously mentioned US$1.8m AFRL radar contract. Raytheon provides services and integration support as BrainChip and AFRL work on the project titled “Mapping Complex Sensor Signal Processing Algorithms onto Neuromorphic Chips”, using Akida for micro-Doppler radar signature analysis and advanced edge radar processing.
• Parsons Corporation (U.S. defence & intelligence prime; includes Blue Ridge Envisioneering) – strategic defence agreement – 23 October 2025
  BrainChip and Parsons (NYSE: PSN), a major U.S. defence and intelligence contractor, signed a multi-year strategic agreement for edge-AI defence systems. Parsons will integrate Akida (including the AKD1500) into its mission-ready edge-AI platforms for tactical defence environments where low-power, on-device learning and real-time inference are required, particularly in constrained, disconnected battle-space scenarios. This agreement also provides Parsons with an AI enablement package, supply continuity, and technical support from BrainChip.

Australian defence-related engagements (publicly visible)




Direct, publicly disclosed contracts with the Australian Defence Force or Department of Defence specifically involving BrainChip are not clearly documented in the same way as the U.S. AFRL and U.S. defence-prime deals above. However, there are some notable Australian defence-science links:

• Defence Science and Technology Group (DSTG – Australia) – Women in STEM Award – late 2022
  At the DICTA 2022 conference, Australia’s DSTG awarded Vi Nguyen Thanh Le from BrainChip the DSTG Women in STEM Award for work on an energy-efficient AkidaNet model for crop/weed recognition at the edge. While not an ADF contract, it reflects DSTG–BrainChip engagement in defence-aligned research and recognition of Akida in defence science circles.

Australian financial/sector analyses consistently classify BrainChip (ASX: BRN) as a “military equipment” or defence-exposed stock, noting its suitability for autonomous vehicles, unmanned aerial surveillance, and defence applications, but they don’t cite specific ADF contracts in the last five years.

———————————————————-

• This list is based on public announcements, ASX filings, and mainstream/industry media.
• Defence, especially in Australia, often involves non-disclosed or classified work, so there may be additional engagements that are not public.
• Where multiple articles describe the same deal (e.g. AFRL contract), I’ve consolidated them into a single bullet.

 

[Pom down under]

From approx 14:25......

"There's some very interesting things that are coming through. I would say simply, stay tuned to us, and watch what we are going to announce later this year. I think you will be amazed by the functionality that we are going to be talking about"......"Later this year/early next year there's a lot of things we are going to be announcing"


View attachment 93394

Wasn’t all this mentioned in the presentation at the AGM?

 

[Pom down under]

Worth highlighting from your post.
" Acumino’s technology is currently in trials with a major German automaker, a large Japanese marine engine producer, and other international manufacturers. “Our system runs on standard robots and hardware and can be deployed on-site with strong data privacy and local control.”"

Isn’t this old news?

 

[7für7]

Ive got a question,
If Mr Heir is stating Watch us Now and there be announcements before years end, why isnt the shareprice going up, Surely people are in the know ?
Why isnt the shareprice going up

I don’t think this has anything to do with what Sean is saying, because many have simply lost confidence. Those who sold after the hype will first want to wait and see if something substantial actually comes.

On top of that, I also think BRN is only on the radar of a small group. Most people have their eyes on NVIDIA, Intel, IBM etc. Even we struggle to find information about BrainChip – so how are outsiders supposed to even notice it?

But what isn’t yet, can still be… just watch us now… the year is almost over