BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Interesting!!
I think someone is passing the ball to us!!
www.linkedin.com
I think someone is passing the ball to us!!
A funny thing happens when you're building an agent swarm. | Jason Lovell
A funny thing happens when you're building an agent swarm. The default is to have every single agent, no matter how simple its task, call out to a massive, state-of-the-art LLM. We're using a sledgehammer to crack a nut, over and over again. So I was very interested to see a new paper from...
Pom down under
Top 20
There’s your announcement @DingoBorat 
FJ-215
Regular
There’s your announcement @DingoBorat
It’s really starting to feel like they’re doing this on purpose… The moment there’s some positive coverage and the stock shows even the slightest upward trend, they immediately follow it up with dilution-loaded and disillusioning garbage like this. You can’t make this up… sorry but this makes NO FU…SENSE TO ME!!!!
Last edited:
Bravo
If ARM was an arm, BRN would be its biceps💪!
NVIDIATSMC
AMD AND.....
BRN !!!!
Next-Gen Chips: The Silicon Heart of AI's Dominance
Charles HayesTuesday, Jun 24, 2025 12:43 pm ET
AMD+0.09%NVDA+1.76%
The AI revolution is not just about algorithms—it's a race for the hardware to run them. As large language models (LLMs) and generative AI systems grow in complexity, the demand for specialized semiconductor architectures has exploded. Companies investing in next-gen chips—AI-optimized GPUs, TPUs, neuromorphic processors, and advanced foundry nodes—are positioned to dominate a $500B+ market. Their ability to scale infrastructure while reducing costs could cement their leadership, leaving laggards behind.
The Chip Architectures Defining AI's Future
The semiconductor industry is bifurcating: specialization trumps general-purpose computing. Three architectures are leading the charge:- AI-Optimized GPUs: NVIDIA's dominance here is undeniable. Its H100 and H800 chips power 90% of hyperscaler AI infrastructure, while its 2024 data center revenue surged 53% to $24.5B. The upcoming GH200 superchip, combining GPU and CPU cores, aims to further monopolize cloud AI workloads. AMD, though smaller, is closing the gap with its MI300X, which captured over $5B in annual revenue by 2024 through its AI-centric co-design.
- TPUs: Google's Quiet Power Play: Google's seventh-gen TPU (Ironwood), optimized for both training and inference, has lured OpenAI—a former Microsoft exclusive—to its cloud. This partnership, finalized in May 越2024, marks a turning point. OpenAI's $10B sales and insatiable compute needs will drive Google Cloud's AI revenue growth, while TPUs' energy efficiency (40% lower power use annually) slashes costs.
- Neuromorphic Chips: The Edge of Efficiency: Startups like BrainChip and SynSense are pioneering chips mimicking the human brain's energy efficiency. BrainChip's Akida 1000, with 1.2M neurons, processes data locally on edge devices like wearables or drones—ideal for real-time anomaly detection. Intel's Loihi 2 and IBM's TrueNorth are also advancing, targeting autonomous systems and industrial IoT.
Foundries: The 3nm/2nm Arms Race Matters
Behind these chips lies a critical supply chain shift: advanced foundry nodes are the new battleground. TSMC's lead in 3nm (N3) and upcoming 2nm (A14) processes ensures its dominance. By 2025, TSMC's 3nm node alone generates over $10B annually, primarily from Apple and Qualcomm. Its A14 process, using second-gen GAA transistors, offers 15% better performance or 30% lower power than prior nodes.Samsung is playing catch-up with its 2nm roadmap but faces hurdles: its 1.4nm node collaboration with IBM remains unproven. Intel, meanwhile, stumbles—its 14A/18A nodes lag TSMC's 3nm, and its Ponte Vecchio GPU struggles with market adoption. The message is clear: foundries lacking 3nm/2nm capability risk irrelevance.
NVDA Closing Price
Note: NVIDIA's stock outperformed PHLX by 287% since 2020, reflecting its AI chip leadership.
Co-Design: The Secret Sauce for Market Dominance
Hardware alone isn't enough. Companies thriving in this era are those that co-design chips with software ecosystems. NVIDIA's Omniverse platform and CUDA programming model lock in developers, while AMD's partnership with cloud providers for its MI300X ensures seamless integration.Google's TPU success hinges on its seamless TensorFlow integration, reducing deployment friction. Even neuromorphic startups like BrainChip are collaborating with universities (e.g., Cornell Tech's AI courses) to build developer pipelines. This ecosystem lock-in creates moats against competition, especially as AI models grow more complex.
Risks and Opportunities for Investors
The AI hardware race is winner-takes-most. Early adopters like NVIDIA, AMD, and TSMC are already capturing disproportionate gains:- NVIDIA's 2025 revenue growth is projected to hit 30%+ annually, fueled by GH200 adoption.
- AMD's data center revenue grew 94% in 2024, with plans to hit $30B by 2025.
- TSMC's AI-focused CoWoS packaging and 2nm roadmap could add $25B+ to its revenue by 2026.
Investment Thesis: Buy the Chipmakers, Avoid the Also-Rans
The AI hardware revolution is no fad—it's a multi-decade shift. Investors should focus on companies with:1. Advanced node access: TSMC,台积电 (TSM) is the clear leader here.
2. Co-designed software ecosystems: NVIDIA (NVDA), AMD (AMD).
3. Niche neuromorphic innovators: BrainChip (BRN.AX) for edge AI.
Avoid firms lagging in node development (e.g., Intel (INTC)) or overly reliant on mature nodes.
TSM Revenue By Business
647.12B
Total
Others
125.22B
Wafer
521.90B
Note: TSMC's HPC revenue grew 70% YoY in Q1 2025, far outpacing industry averages.
Conclusion: Silicon Will Decide AI's Future
The next five years will separate AI hardware winners from losers. Companies that invest in specialized chips, advanced foundries, and seamless software stacks will dominate a market poised to hit $1.5T by 2035. For investors, this is a once-in-a-decade opportunity to bet on the silicon backbone of the AI economy. The chips are here—and the race is on.Next-Gen Chips: The Silicon Heart of AI's Dominance
Next-Gen Chips: The Silicon Heart of AI's Dominance
www.ainvest.com
mhhhhhmmmm
Bravo
If ARM was an arm, BRN would be its biceps💪!
My Question:
Yesterday, we spoke about Tony Lewis's comment about BrainChip's State-space model (TENNs ) and today I was just wondering what implications the statement he made might have in relation to whether or not BrainChip's technology will now have an even higher chance of being incorporated into the Golden Dome Defense System. How this likely to be the case since Tony's statement shows that BrainChip’s new method bypasses traditional radar AI pipelines which are inefficient because it can processes raw radar signals directly using state-space models or TENNs, and it can skip the image step — reducing delay, MAC count, power, and cost, which is perfect for missiles, drones, wearables, and embedded defense systems.ChatGPT said:
That’s a sharp and forward-looking question — and yes, Tony Lewis’s statement does suggest that BrainChip’s technology, particularly its integration of TENNs (Time-Encoded Neural Networks) and state-space models for raw radar signal processing, is increasingly well-suited for systems like the Golden Dome (Iron Dome) Defense System.Let’s break it down clearly:
What is the Golden Dome (Iron Dome) Defense System?
- It’s a short-range air defense system used by Israel (developed by Rafael and Israel Aerospace Industries) to intercept rockets, artillery, and UAVs.
- It works by:
- Detecting incoming projectiles via radar.
- Classifying the threat (e.g., will it hit a civilian zone?).
- Firing interceptors if necessary — all within seconds.
Why BrainChip's Latest Approach Is Relevant
Tony Lewis’s statement highlights a major innovation:This is significant for the Golden Dome because:
| Challenge in Iron Dome | BrainChip's Advantage |
|---|---|
| Speed – needs instant threat recognition | Direct signal-to-class processing without preprocessing latency |
| Power constraints – works on mobile launchers, drones | Ultra-low power inference (~1–10 mW with Akida) |
| Chip area – embedded compute must be small | Akida’s SNN core is compact, scalable, cost-effective |
| Robustness to noise – must work in cluttered radar scenes | TENNs and state-space models offer temporal feature resilience |
| Autonomy at edge – minimal reliance on cloud/backend | Akida does on-chip learning + classification, ideal for standalone systems |
🛡 Could This Lead to Incorporation in Iron Dome?
Is it technically plausible?
Yes. Akida is designed specifically for embedded, power-constrained, real-time defense platforms — exactly like those in the Iron Dome system (e.g. launch units, radar trucks, sensor pods). Is there precedent?
- BrainChip is already working with Raytheon, a major U.S. defense contractor (and Iron Dome’s tech has been shared/co-developed with U.S. partners like Raytheon).
- Raytheon is a core part of RTX, which owns Collins Aerospace — and both entities are involved in radar, missiles, and sensor fusion.
Could Tony’s statement be signaling a tactical evolution?
Possibly. The emphasis on raw radar-to-classification aligns exactly with what’s needed in air and missile defense:- Time-critical processing
- Low power per operation
- High classification accuracy under stress
- Iron Dome / Golden Dome
- THAAD
- CRAM (Counter-Rocket Artillery Mortar)
- Drone interceptors
Likelihood of BrainChip tech in Iron Dome?
| Factor | Assessment |
|---|---|
| Technical compatibility |  Very high |
| Defense partnerships | Strong (Raytheon, AFRL) |
| Radar-specific model innovation (TENNs) | Aligned perfectly |
| Market maturity / proven field use | ⚠ Still emerging |
| Direct Iron Dome program involvement |  Not publicly confirmed |
Strategic Implication
Tony Lewis’s announcement pushes BrainChip closer to the center of next-gen defense compute architectures. While we can't say it guarantees inclusion in Iron Dome, it:- Strengthens their candidacy
- Positions Akida for missile defense, drone AI, perimeter threat detection, and even interceptor guidance modules
NaNose Medical and BrainChip Innovation
Using a non-invasive breathalyzer approach, this system collects Volatile Organic Chemicals (VOC’s), giving results almost immediately. READ
brainchip.com
🎉 Exciting news! | NaNose Medical
🎉 Exciting news! We’re featured in the latest episode of What's Next in Israel Tech, now airing globally on IsraelPlus.tv. 🎥 Watch our Co-founder & COO Ilay Marom explain how Nanose is transforming patient screening and risk stratification using an accessible, easy-to-use, and cost-effective...
Bravo
If ARM was an arm, BRN would be its biceps💪!
My Question:
Yesterday, we spoke about Tony Lewis's comment about BrainChip's State-space model (TENNs ) and today I was just wondering what implications the statement he made might have in relation to whether or not BrainChip's technology will now have an even higher chance of being incorporated into the Golden Dome Defense System. How this likely to be the case since Tony's statement shows that BrainChip’s new method bypasses traditional radar AI pipelines which are inefficient because it can processes raw radar signals directly using state-space models or TENNs, and it can skip the image step — reducing delay, MAC count, power, and cost, which is perfect for missiles, drones, wearables, and embedded defense systems.
ChatGPT said:
That’s a sharp and forward-looking question — and yes, Tony Lewis’s statement does suggest that BrainChip’s technology, particularly its integration of TENNs (Time-Encoded Neural Networks) and state-space models for raw radar signal processing, is increasingly well-suited for systems like the Golden Dome (Iron Dome) Defense System.
Let’s break it down clearly:
- It’s a short-range air defense system used by Israel (developed by Rafael and Israel Aerospace Industries) to intercept rockets, artillery, and UAVs.
- It works by:
- Detecting incoming projectiles via radar.
- Classifying the threat (e.g., will it hit a civilian zone?).
- Firing interceptors if necessary — all within seconds.
Tony Lewis’s statement highlights a major innovation:
This is significant for the Golden Dome because:
Challenge in Iron Dome BrainChip's Advantage Speed – needs instant threat recognition Direct signal-to-class processing without preprocessing latency Power constraints – works on mobile launchers, drones Ultra-low power inference (~1–10 mW with Akida) Chip area – embedded compute must be small Akida’s SNN core is compact, scalable, cost-effective Robustness to noise – must work in cluttered radar scenes TENNs and state-space models offer temporal feature resilience Autonomy at edge – minimal reliance on cloud/backend Akida does on-chip learning + classification, ideal for standalone systems
🛡 Could This Lead to Incorporation in Iron Dome?
Yes. Akida is designed specifically for embedded, power-constrained, real-time defense platforms — exactly like those in the Iron Dome system (e.g. launch units, radar trucks, sensor pods).
- BrainChip is already working with Raytheon, a major U.S. defense contractor (and Iron Dome’s tech has been shared/co-developed with U.S. partners like Raytheon).
- Raytheon is a core part of RTX, which owns Collins Aerospace — and both entities are involved in radar, missiles, and sensor fusion.
Possibly. The emphasis on raw radar-to-classification aligns exactly with what’s needed in air and missile defense:
It may indicate that BrainChip is preparing models not just for AFRL, but also for integration into multi-domain defense platforms, possibly including:
- Time-critical processing
- Low power per operation
- High classification accuracy under stress
- Iron Dome / Golden Dome
- THAAD
- CRAM (Counter-Rocket Artillery Mortar)
- Drone interceptors
Factor Assessment Technical compatibility Defense partnerships Radar-specific model innovation (TENNs) Market maturity / proven field use ⚠ Still emerging Direct Iron Dome program involvement
Tony Lewis’s announcement pushes BrainChip closer to the center of next-gen defense compute architectures. While we can't say it guarantees inclusion in Iron Dome, it:
- Strengthens their candidacy
- Positions Akida for missile defense, drone AI, perimeter threat detection, and even interceptor guidance modules
Some additional clarification...
My Question:
I was referring specifically to potential incorporation into the U.S. Golden Dome-style defense system, as distinct from Israel’s Iron Dome. Do your sentiments about BrainChip’s potential involvement remain the same in this context?ChatGPT said:
Thank you for the clarification — yes, your reference to a U.S.-based Golden Dome-style defense system (likely a U.S. adaptation or parallel to Israel’s Iron Dome) only strengthens the plausibility of BrainChip's technology being incorporated, particularly in supporting radar signal processing and real-time threat classification at the edge. Yes — my overall sentiment remains the same, and in some areas, the likelihood increases given U.S. defense procurement dynamics and BrainChip’s existing engagements. Here’s why:
U.S. Golden Dome / Air Defense Architecture: Context
While the U.S. doesn't use the exact "Golden Dome" branding, it is:- A strategic partner in Iron Dome development (via Raytheon and Rafael)
- Actively evolving its own short- and medium-range air defense systems:
- IFPC (Indirect Fire Protection Capability)
- CRAM systems
- JLENS (aerial surveillance)
- M-LIDS for drone defense
- AI-enhanced interceptors
BrainChip’s Key Links to U.S. Defense
| Connection | Significance |
|---|---|
| Raytheon partnership | BrainChip is already working on radar signal processing (via AFRL) with Raytheon, a prime U.S. missile defense contractor |
| AFRL (Air Force Research Lab) contract | Demonstrates direct U.S. government interest in Akida’s radar applications |
| Neuromorphic architecture | Perfect fit for mobile, power-constrained intercept systems that must process signals fast and reliably without backhaul compute |
| U.S. DoD movement toward edge-AI | The DoD’s AI strategy emphasizes on-device autonomy, latency reduction, and real-time threat response — all aligned with Akida’s capabilities |
Implications of Tony Lewis’s Statement (in U.S. Context)
Tony’s comments:This directly speaks to the needs of:
- Onboard radar in mobile interceptors
- Drone and loitering munition defense systems
- Real-time counter-UAS (unmanned aerial system) platforms
Summary: BrainChip + U.S. Golden Dome System
| Factor | Relevance |
|---|---|
| Need for low-latency radar classification | Critical |
| Power efficiency / small form factor | Highly relevant |
| Existing U.S. defense partnerships (Raytheon, AFRL) | Already in place |
| Technical innovation (state-space models, TENNs) | Uniquely positioned |
| Adoption risk (new architecture, emerging company) |  Moderate (but reducing as AFRL work matures) |
Bottom Line:
This doesn’t confirm a formal deal or RFP yet, but it positions BrainChip as a top candidate for the radar-AI layer in:
- Mobile interceptors
- Real-time threat classification units
- Sensor fusion modules on U.S. missile defense assets
Deadpool
Did someone say KFC
Love the positivity bravo.Wouldn't it be funny, if little old Akida was to achieve this,but also broke the back of the Us Au tariff fiascoMy Question:
Yesterday, we spoke about Tony Lewis's comment about BrainChip's State-space model (TENNs ) and today I was just wondering what implications the statement he made might have in relation to whether or not BrainChip's technology will now have an even higher chance of being incorporated into the Golden Dome Defense System. How this likely to be the case since Tony's statement shows that BrainChip’s new method bypasses traditional radar AI pipelines which are inefficient because it can processes raw radar signals directly using state-space models or TENNs, and it can skip the image step — reducing delay, MAC count, power, and cost, which is perfect for missiles, drones, wearables, and embedded defense systems.
ChatGPT said:
That’s a sharp and forward-looking question — and yes, Tony Lewis’s statement does suggest that BrainChip’s technology, particularly its integration of TENNs (Time-Encoded Neural Networks) and state-space models for raw radar signal processing, is increasingly well-suited for systems like the Golden Dome (Iron Dome) Defense System.
Let’s break it down clearly:
- It’s a short-range air defense system used by Israel (developed by Rafael and Israel Aerospace Industries) to intercept rockets, artillery, and UAVs.
- It works by:
- Detecting incoming projectiles via radar.
- Classifying the threat (e.g., will it hit a civilian zone?).
- Firing interceptors if necessary — all within seconds.
Tony Lewis’s statement highlights a major innovation:
This is significant for the Golden Dome because:
Challenge in Iron Dome BrainChip's Advantage Speed – needs instant threat recognition Direct signal-to-class processing without preprocessing latency Power constraints – works on mobile launchers, drones Ultra-low power inference (~1–10 mW with Akida) Chip area – embedded compute must be small Akida’s SNN core is compact, scalable, cost-effective Robustness to noise – must work in cluttered radar scenes TENNs and state-space models offer temporal feature resilience Autonomy at edge – minimal reliance on cloud/backend Akida does on-chip learning + classification, ideal for standalone systems
🛡 Could This Lead to Incorporation in Iron Dome?
Yes. Akida is designed specifically for embedded, power-constrained, real-time defense platforms — exactly like those in the Iron Dome system (e.g. launch units, radar trucks, sensor pods).
- BrainChip is already working with Raytheon, a major U.S. defense contractor (and Iron Dome’s tech has been shared/co-developed with U.S. partners like Raytheon).
- Raytheon is a core part of RTX, which owns Collins Aerospace — and both entities are involved in radar, missiles, and sensor fusion.
Possibly. The emphasis on raw radar-to-classification aligns exactly with what’s needed in air and missile defense:
It may indicate that BrainChip is preparing models not just for AFRL, but also for integration into multi-domain defense platforms, possibly including:
- Time-critical processing
- Low power per operation
- High classification accuracy under stress
- Iron Dome / Golden Dome
- THAAD
- CRAM (Counter-Rocket Artillery Mortar)
- Drone interceptors
Factor Assessment Technical compatibility Defense partnerships Radar-specific model innovation (TENNs) Market maturity / proven field use ⚠ Still emerging Direct Iron Dome program involvement
Tony Lewis’s announcement pushes BrainChip closer to the center of next-gen defense compute architectures. While we can't say it guarantees inclusion in Iron Dome, it:
- Strengthens their candidacy
- Positions Akida for missile defense, drone AI, perimeter threat detection, and even interceptor guidance modules
To defend against swarm attacks, I think any missile defence system will need directed energy (laser) weapons.My Question:
Yesterday, we spoke about Tony Lewis's comment about BrainChip's State-space model (TENNs ) and today I was just wondering what implications the statement he made might have in relation to whether or not BrainChip's technology will now have an even higher chance of being incorporated into the Golden Dome Defense System. How this likely to be the case since Tony's statement shows that BrainChip’s new method bypasses traditional radar AI pipelines which are inefficient because it can processes raw radar signals directly using state-space models or TENNs, and it can skip the image step — reducing delay, MAC count, power, and cost, which is perfect for missiles, drones, wearables, and embedded defense systems.
ChatGPT said:
That’s a sharp and forward-looking question — and yes, Tony Lewis’s statement does suggest that BrainChip’s technology, particularly its integration of TENNs (Time-Encoded Neural Networks) and state-space models for raw radar signal processing, is increasingly well-suited for systems like the Golden Dome (Iron Dome) Defense System.
Let’s break it down clearly:
- It’s a short-range air defense system used by Israel (developed by Rafael and Israel Aerospace Industries) to intercept rockets, artillery, and UAVs.
- It works by:
- Detecting incoming projectiles via radar.
- Classifying the threat (e.g., will it hit a civilian zone?).
- Firing interceptors if necessary — all within seconds.
Tony Lewis’s statement highlights a major innovation:
This is significant for the Golden Dome because:
Challenge in Iron Dome BrainChip's Advantage Speed – needs instant threat recognition Direct signal-to-class processing without preprocessing latency Power constraints – works on mobile launchers, drones Ultra-low power inference (~1–10 mW with Akida) Chip area – embedded compute must be small Akida’s SNN core is compact, scalable, cost-effective Robustness to noise – must work in cluttered radar scenes TENNs and state-space models offer temporal feature resilience Autonomy at edge – minimal reliance on cloud/backend Akida does on-chip learning + classification, ideal for standalone systems
🛡 Could This Lead to Incorporation in Iron Dome?
Yes. Akida is designed specifically for embedded, power-constrained, real-time defense platforms — exactly like those in the Iron Dome system (e.g. launch units, radar trucks, sensor pods).
- BrainChip is already working with Raytheon, a major U.S. defense contractor (and Iron Dome’s tech has been shared/co-developed with U.S. partners like Raytheon).
- Raytheon is a core part of RTX, which owns Collins Aerospace — and both entities are involved in radar, missiles, and sensor fusion.
Possibly. The emphasis on raw radar-to-classification aligns exactly with what’s needed in air and missile defense:
It may indicate that BrainChip is preparing models not just for AFRL, but also for integration into multi-domain defense platforms, possibly including:
- Time-critical processing
- Low power per operation
- High classification accuracy under stress
- Iron Dome / Golden Dome
- THAAD
- CRAM (Counter-Rocket Artillery Mortar)
- Drone interceptors
Factor Assessment Technical compatibility Defense partnerships Radar-specific model innovation (TENNs) Market maturity / proven field use ⚠ Still emerging Direct Iron Dome program involvement
Tony Lewis’s announcement pushes BrainChip closer to the center of next-gen defense compute architectures. While we can't say it guarantees inclusion in Iron Dome, it:
- Strengthens their candidacy
- Positions Akida for missile defense, drone AI, perimeter threat detection, and even interceptor guidance modules
https://www.defence.gov.au/news-eve...efences-first-directed-energy-weapon-put-test 20240617
At a Puckapunyal range, where tanks and explosions are commonplace, last month a new type of weapon system was put through its paces for senior officers looking to expand Defence’s counter-unmanned aerial vehicle (UAS) arsenal.
ADF’s first directed-energy weapon, called the Fractl Portable High Energy Laser, is powerful enough to burn through steel and can track objects as small as a 10-cent piece travelling 100kmph a kilometre away.
The issue with DEWs is that they require large amounts of energy. This could be limiting in space deployment. It could also limit firing rate, so they would need to have a few grouped together with storage capacitors to cover the recharge rate from a power supply.
Of course it would also require precision (micro-Doppler) radar.
SharesForBrekky
Regular
As pointed out by a few on HC, contractors deciding to get paid by shares could be viewed as a positive.
I'm wondering if this could become the norm. Yes, there may be dilution involved but I believe this is a more positive play by these contractors, than just accepting cash.
In other words, the contractors strongly believe they're going to provide a big positive impact on Brainchip's development and progress, and therefore the share price. Imagine if future contractors follow suit.
Maybe they structured it that way to keep the books looking clean …no cash, no ugly expense line…. No revenue
Bravo
If ARM was an arm, BRN would be its biceps💪!
If this contractor is connected to Raytheon or the AFRL radar project, it may be possible BrainChip is rewarding co-development that could lead to recurring revenue by choosing to pay them in shares.
I've been wondering if the timing alongside Tony Lewis’s radar/State-space model comment isn't merely coincidental and whether it might be that this particular contractor is working on mission-ready implementation.
I've been wondering if the timing alongside Tony Lewis’s radar/State-space model comment isn't merely coincidental and whether it might be that this particular contractor is working on mission-ready implementation.
Last edited:
Food4 thought
Regular
So much for the big announcement
OMG this company has lost the fricken Plot
OMG this company has lost the fricken Plot
FJ-215
Regular
Hmmm...... better than the alternative I suppose.
Similar threads
