BRN Discussion Ongoing

[Guzzi62]

The company is pushing 1500. The new version will be TENNs compatible. I'm guessing that they have uncovered strong market demand for this. This will be up to 4-bit precision. Akida 2 has 8-bit, so the application does not require that degree of accuracy. 1500 can be used with other CPUs (including RISC-V) as well as ARM.

There may be a big customer, but I doubt we would make chips for just one customer ...

... those blasted blackbirds have eaten the rest of the breadcrumbs.

Why do you think it will be TENNs compatible? That would be awesome if it did.

https://brainchip.com/wp-content/uploads/2025/10/AKD1500-Product-Brief-V2.4-Oct.25.pdf

 

[TECH]

Doesn't our company have a legally binding agreement with LDA Capital that is still open?

Just asking for a friend

Tech.

 

[Pom down under]

Doesn't our company have a legally binding agreement with LDA Capital that is still open?

Just asking for a friend

Tech.

A while back wasn’t they still holding onto quite a few on the top 100 holders list? They must have been unable to lend them, ooops I mean sell them for the required price, maybe someone has the latest top 100

 

[Diogenese]

Why do you think it will be TENNs compatible? That would be awesome if it did.

https://brainchip.com/wp-content/uploads/2025/10/AKD1500-Product-Brief-V2.4-Oct.25.pdf

1. We are taping out a new 1500.
2. The original 1500 is the same as the original 1000 minus the ARM Cortex processor
3. The new 1000 datasheet shows "support for 128 MACs" (MAC-Lite).
4. Presumably the new 1500 tapeout will be the same as the new 1000 minus the ARM Cortex.
5. Initially, BRN could not do recurrence with TENNs.
6. Recurrence is used in ML with TENNs.
7. The new 1500 can do ML.
8. My assumption is that the MACs enable recurrence with TENNs in the new 1500.

If this is correct, I suspect the new tapeout will be a total rebuild from the ground up, rather than just a tweak of the old 1500 tapeout .

 

[Newk R]

Time will tell… until then, empty talk I would say

No doubt we’re well positioned..but I don’t think this announcement changes that something big will follow. I’m preparing for another year of a dry spell. After more than a decade with BrainChip, that’s been my experience. I’d love to be proven wrong.
But I stopped long time ago listen every time the same stuff “this will be huge” “this time is different” “something is brewing” etc. that’s all

Hi 7,
I follow a football team in Australia called Collingwood. The biggest club and the most successful in the land. We won a premiership cup in 1958 and then the biggest (at the time) cup drought ensued. 32 years. During that period, we had a saying.."we'll win it next year".
I am fearing that BRN is my new Collingwood....I hope not.

 

[7für7]

Hi 7,
I follow a football team in Australia called Collingwood. The biggest club and the most successful in the land. We won a premiership cup in 1958 and then the biggest (at the time) cup drought ensued. 32 years. During that period, we had a saying.."we'll win it next year".
I am fearing that BRN is my new Collingwood....I hope not.

I’m very confident BrainChip will find its way. The technology speaks for itself. I just hope the company doesn’t abandon those of us who’ve been on board for a long time. I’ve watched plenty of promising companies that ended up pulling the rug on small investors—using reverse splits (RS) that shrank early holders into insignificance. Then new investors (sometimes the very short sellers from before, plus institutions) step in once the dilution is “done” and short interest drops, and only then do the companies unveil their big deals—price goes up afterward. I hope BrainChip isn’t one of those stories. Just my opinion, based on what I’ve seen in the market.

Edit. That’s why I buy more , so a possible RS will not hurt me too much

 

[Guzzi62]

1. We are taping out a new 1500.
2. The original 1500 is the same as the original 1000 minus the ARM Cortex processor
3. The new 1000 datasheet shows "support for 128 MACs" (MAC-Lite).
4. Presumably the new 1500 tapeout will be the same as the new 1000 minus the ARM Cortex.
5. Initially, BRN could not do recurrence with TENNs.
6. Recurrence is used in ML with TENNs.
7. The new 1500 can do ML.
8. My assumption is that the MACs enable recurrence with TENNs in the new 1500.

If this is correct, I suspect the new tapeout will be a total rebuild from the ground up, rather than just a tweak of the old 1500 tapeout .

Thanks, but I am still not convinced that's the case.

The PDF is from Oct25, so I will assume that's the specs that will be in the production AK1500 and not a word about TENNs?
If it can do TENNs I am sure they will mention it.

But okay, we will find out sometime next year.

https://brainchip.com/wp-content/uploads/2025/10/AKD1500-Product-Brief-V2.4-Oct.25.pdf