bascomhunter.com
Doz
3U VPX SNAP Card
Bascom Hunter's 3U VPX SNAP Card combines a Xilinx RFSoC FPGA with BrainChip neuromorphic processors for rugged, low-power AI/ML performance in mission-critical defense applications.
IPO later this year for all Musk’s space related companies including Starlink under one umbrella. Huge news if we turn out to be involved with Starlink. The merger company according to Bloomberg could be valued at around 1.5 trillion making it the biggest IPO in history.Does anyone know which neuromorphic chips might be being referred to here?
Starlink and neuromorphic chips ...?
#starlinkneuromorphic #spacexinnovation #neuromorphiccomputing #aerospaceai #connectivityfuture | Daniel Azevedo Novais
Decoding Starlink's Neuromorphic Revolution: Brain-Inspired Chips Powering the Next Era of Orbital Dominance Imagine a constellation of satellites not just relaying data, but thinking like a human brain—efficiently, autonomously, and with minimal power—in the unforgiving vacuum of space. As we...www.linkedin.com
But in space, no one can hear your phonics.I just saw this article highlighting a new edge-AI tech from Brisbane-based startup Cortisonic, which is backed by Lockheed Martin. It sounds like it's a completely different technology to BrainChip’s Akida.
It says in the article " Unlike other experimental computing efforts, Cortisonic’s chips are compatible with existing semiconductor manufacturing.The team has already fabricated a 10,000-node phonon-based processor using standard tools."
It says "Edge devices such as autonomous drones, satellite systems, wearables and embedded cameras demand real-time processing but lack the power budgets of server racks. Cortisonic sees a clear path to market by targeting these constraints rather than competing head-on with existing GPU manufacturers."
Fortunately Cortisonic seem a bit further behind us because they're still in demonstration phase. It says "Cortisonic’s acoustic computing chips are still in the demonstration phase, but the company believes it has the technical and commercial backing to move from prototype to product, with ambitions to become a foundational player in next-generation AI deployments across defence, aerospace and embedded systems."
It also says they're not seeking to to displace incumbent chips but rather "the startup sees its platform as a complementary tool that extends where AI can be deployed, especially in constrained edge environments." Sounds similar to how Akida is being pitched as a complementary coprocessor.
I don't think it means BrainChip has lost a potential Lockheed-related partnership. It's probably more likely to reflect broader innovation and competition in the ultra low-power edge AI space.
Cortisonic Launches Lockheed Martin-Backed Sonic Chip For Edge AI In Harsh Environments
Cortisonic Launches Lockheed Martin-Backed Sonic Chip For Edge AI In Harsh Environments
Nick Ross February 2, 2026 News
Brisbane-based startup Cortisonic has stepped out of stealth mode with a new computing architecture that swaps electrons for sound waves, targeting the energy limitations of traditional AI hardware.
Its Sonic Processing Unit (SPU) replaces electrical signals with phonons – quantised sound waves – to conduct computations in silicon, offering ultra-low-power AI performance suitable for space-constrained edge devices like drones, wearables and satellites.
A Push Against AI’s Power Wall
“AI’s energy consumption is rising sharply, creating a major bottleneck for deployment,” said Dr Glen Harris, Chief Executive of Cortisonic.
“Data centres are consuming power at the scale of entire nations. We’re not pursuing incremental improvements to existing chips – we’re introducing an entirely new computational element to the mix.”
While GPUs and photonic chips have long been viewed as the workhorses of AI workloads, their power draw and thermal limits prevent broad deployment in edge scenarios. Phononic computing sidesteps the same energy thresholds that cap performance in electron- and photon-based systems.
“Our acoustic platform uses phonons to fill the gaps where electronics and photonics hit power constraints, unlocking sophisticated AI in environments where it’s been impossible until now,” Harris said.
Backed By Defence, Built With Silicon Tools
Cortisonic’s entry comes with backing from CSIRO-linked venture fund Main Sequence and Lockheed Martin. The company has secured a $3.2 million contract under the Department of Defence’s Advanced Strategic Capabilities Accelerator (ASCA), in partnership with Lockheed Martin Australia.
Unlike other experimental computing efforts, Cortisonic’s chips are compatible with existing semiconductor manufacturing. The team has already fabricated a 10,000-node phonon-based processor using standard tools.
“Cortisonic is not inventing new materials or requiring cryogenic systems,” said Dr Tony Lindsay, Director of Advanced Systems & Technologies at Lockheed Martin Australia. “The acoustic wave platform offers a completely new approach with strong potential to deliver mission-critical capability with exceptional efficiency, which is vital for space-based and tactical edge assets.”
The startup aims to demonstrate a minimum viable capability (MVC) within two years.
Targeting The Edge, Not The Data Centre
Despite AI infrastructure concerns typically focusing on data centre expansion, Cortisonic is zeroing in on edge computing – a market forecast to grow to $270 billion by 2032.
“You can’t put a data centre on a drone or into a wearable device,” said Harris. “Any portable, low-power application where you don’t have abundant resources is where we excel.”
Edge devices such as autonomous drones, satellite systems, wearables and embedded cameras demand real-time processing but lack the power budgets of server racks. Cortisonic sees a clear path to market by targeting these constraints rather than competing head-on with existing GPU manufacturers.
Years In The Making
The technology builds on eight years of foundational research conducted with the University of Queensland’s School of Mathematics and Physics, with commercialisation handled through UniQuest. Cortisonic was spun out under Main Sequence’s Venture Science model.
Its leadership team includes Dr Chris Baker as Chief Scientist and Dr Michael Harvey as Chief Technology Officer.
Alex Romero, Investment Manager at Main Sequence, said the company’s approach reflects a shift toward physics-led innovation in AI.
“The combination of foundational IP, commercially scalable manufacturing, early validation from Lockheed Martin, and dedicated government funding gives them unique credibility as they emerge from stealth to reshape the future of edge computing.”
Sonic Processing Unit: A New Architecture
Cortisonic describes its architecture as an SPU – a Sonic Processing Unit – distinguishing it from more traditional GPUs, CPUs and TPUs.
“We’re introducing phonons into the mix of computational elements,” Harris said. “It’s about using all the particles at your disposal – electrons, photons and now phonons – to do computing more efficiently.”
Rather than seeking to displace incumbent chips, the startup sees its platform as a complementary tool that extends where AI can be deployed, especially in constrained edge environments.
Cortisonic’s acoustic computing chips are still in the demonstration phase, but the company believes it has the technical and commercial backing to move from prototype to product, with ambitions to become a foundational player in next-generation AI deployments across defence, aerospace and embedded systems.
Thanks for posting this. I read the whole thing, and agree it makes some very good points, essentially mapping the path to 1. Growth of neuromorphics and 2 mapping the paradigm shift, redesigning the whole computing ecosystem from first principles for optimum AGI, which would happen to have neuromorphics at the core. Some very good prompting on display, worth the read.
A Chat with GPT: Brainchip Akida versus GPU / TPU technology
BrainChip, Akida, and Edge AI—why the GPU “steam engine” era may yield to neuromorphic “internal combustion”: faster, frugal, event-driven.jwpm.com.au
I just saw this article highlighting a new edge-AI tech from Brisbane-based startup Cortisonic, which is backed by Lockheed Martin. It sounds like it's a completely different technology to BrainChip’s Akida.
It says in the article " Unlike other experimental computing efforts, Cortisonic’s chips are compatible with existing semiconductor manufacturing.The team has already fabricated a 10,000-node phonon-based processor using standard tools."
It says "Edge devices such as autonomous drones, satellite systems, wearables and embedded cameras demand real-time processing but lack the power budgets of server racks. Cortisonic sees a clear path to market by targeting these constraints rather than competing head-on with existing GPU manufacturers."
Fortunately Cortisonic seem a bit further behind us because they're still in demonstration phase. It says "Cortisonic’s acoustic computing chips are still in the demonstration phase, but the company believes it has the technical and commercial backing to move from prototype to product, with ambitions to become a foundational player in next-generation AI deployments across defence, aerospace and embedded systems."
It also says they're not seeking to to displace incumbent chips but rather "the startup sees its platform as a complementary tool that extends where AI can be deployed, especially in constrained edge environments." Sounds similar to how Akida is being pitched as a complementary coprocessor.
I don't think it means BrainChip has lost a potential Lockheed-related partnership. It's probably more likely to reflect broader innovation and competition in the ultra low-power edge AI space.
Cortisonic Launches Lockheed Martin-Backed Sonic Chip For Edge AI In Harsh Environments
Cortisonic Launches Lockheed Martin-Backed Sonic Chip For Edge AI In Harsh Environments
Nick Ross February 2, 2026 News
Brisbane-based startup Cortisonic has stepped out of stealth mode with a new computing architecture that swaps electrons for sound waves, targeting the energy limitations of traditional AI hardware.
Its Sonic Processing Unit (SPU) replaces electrical signals with phonons – quantised sound waves – to conduct computations in silicon, offering ultra-low-power AI performance suitable for space-constrained edge devices like drones, wearables and satellites.
A Push Against AI’s Power Wall
“AI’s energy consumption is rising sharply, creating a major bottleneck for deployment,” said Dr Glen Harris, Chief Executive of Cortisonic.
“Data centres are consuming power at the scale of entire nations. We’re not pursuing incremental improvements to existing chips – we’re introducing an entirely new computational element to the mix.”
While GPUs and photonic chips have long been viewed as the workhorses of AI workloads, their power draw and thermal limits prevent broad deployment in edge scenarios. Phononic computing sidesteps the same energy thresholds that cap performance in electron- and photon-based systems.
“Our acoustic platform uses phonons to fill the gaps where electronics and photonics hit power constraints, unlocking sophisticated AI in environments where it’s been impossible until now,” Harris said.
Backed By Defence, Built With Silicon Tools
Cortisonic’s entry comes with backing from CSIRO-linked venture fund Main Sequence and Lockheed Martin. The company has secured a $3.2 million contract under the Department of Defence’s Advanced Strategic Capabilities Accelerator (ASCA), in partnership with Lockheed Martin Australia.
Unlike other experimental computing efforts, Cortisonic’s chips are compatible with existing semiconductor manufacturing. The team has already fabricated a 10,000-node phonon-based processor using standard tools.
“Cortisonic is not inventing new materials or requiring cryogenic systems,” said Dr Tony Lindsay, Director of Advanced Systems & Technologies at Lockheed Martin Australia. “The acoustic wave platform offers a completely new approach with strong potential to deliver mission-critical capability with exceptional efficiency, which is vital for space-based and tactical edge assets.”
The startup aims to demonstrate a minimum viable capability (MVC) within two years.
Targeting The Edge, Not The Data Centre
Despite AI infrastructure concerns typically focusing on data centre expansion, Cortisonic is zeroing in on edge computing – a market forecast to grow to $270 billion by 2032.
“You can’t put a data centre on a drone or into a wearable device,” said Harris. “Any portable, low-power application where you don’t have abundant resources is where we excel.”
Edge devices such as autonomous drones, satellite systems, wearables and embedded cameras demand real-time processing but lack the power budgets of server racks. Cortisonic sees a clear path to market by targeting these constraints rather than competing head-on with existing GPU manufacturers.
Years In The Making
The technology builds on eight years of foundational research conducted with the University of Queensland’s School of Mathematics and Physics, with commercialisation handled through UniQuest. Cortisonic was spun out under Main Sequence’s Venture Science model.
Its leadership team includes Dr Chris Baker as Chief Scientist and Dr Michael Harvey as Chief Technology Officer.
Alex Romero, Investment Manager at Main Sequence, said the company’s approach reflects a shift toward physics-led innovation in AI.
“The combination of foundational IP, commercially scalable manufacturing, early validation from Lockheed Martin, and dedicated government funding gives them unique credibility as they emerge from stealth to reshape the future of edge computing.”
Sonic Processing Unit: A New Architecture
Cortisonic describes its architecture as an SPU – a Sonic Processing Unit – distinguishing it from more traditional GPUs, CPUs and TPUs.
“We’re introducing phonons into the mix of computational elements,” Harris said. “It’s about using all the particles at your disposal – electrons, photons and now phonons – to do computing more efficiently.”
Rather than seeking to displace incumbent chips, the startup sees its platform as a complementary tool that extends where AI can be deployed, especially in constrained edge environments.
Cortisonic’s acoustic computing chips are still in the demonstration phase, but the company believes it has the technical and commercial backing to move from prototype to product, with ambitions to become a foundational player in next-generation AI deployments across defence, aerospace and embedded systems.
Yes, interesting article but I'm thinking we hitched a ride under the ANT61 banner rather than a direct request from SpaceX
Are you surprised?What I can read from various articles involved new startups in this field, if Brainchip don’t move it’s a..s immediately, we will be f…ed…
I have the feeling while other companies make real world progress , catching up our partner’s silently, our company is eating popcorn and drinking beer In terms of sales …. WTF
Kevin D. Johnson is legit. This not a scam. See recent article he wrote on Symphony. No mention of AKIDA but had to rule out a scam possibility.
