Ben Thompson

speaker

42,103 appearances 120 recordings 2 series first heard Sep 2024 last heard 21 Aug

Ben Thompson’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 39 in all, peaking in Mar 2026 with 5.

Appearances

newest first · ▶ plays the moment

Sharp Tech with Ben Thompson · (Preview) Inference in the Agentic Future, xAI Is Two Companies in One, Q&A on Elon’s Lawsuit, Intel, Apple · 15 May 2026 podcast

And it's like it everything's all it's wild stuff. podcast-host

Yeah. podcast-host

It's it's a really interesting approach to get. podcast-host

sort of a lot of compute and a lot of S RAM, like the the super fast on the chip RAM, which is what Grok does also, but Grok is still limited by the reticle limit. podcast-host

So they're they're they're Grok is more uh systemizing putting different ones together. podcast-host

Super s like, no one way for one chip. podcast-host

And then they're they're uh you get allows them to serve stuff faster podcast-host

Unbelievably fast. podcast-host

Like, like this is like this this solves. podcast-host

So there's different aspects of the inference process, but there's parts of it that are just extremely limited by bandwidth of like how fast you can get memory into the processor and move on to the next step. podcast-host

And they're unbelievably fast at that. podcast-host

Like, like orders of magnitude faster than than other sort of approaches. podcast-host

But podcast-host

There's limitations. podcast-host

Like you're limited by how much memory you can fit on that chip. podcast-host

And the moment you're going off the chip, like your performance is totally plummeting. podcast-host

Right. podcast-host

So uh it's definitely a narrow use case, but there's situations where if you want immediate response and not just an immediate response, but immediate, like sort of like thinking through things sort of response, it makes a lot of sense. podcast-host

But then if you're reasoning and you're doing stuff, it's not just the size of the model fitting on the chip, but the KV cache, which is like all the context of the conversation, that gets large very quickly. podcast-host

There's lots of limitations, but podcast-host

Showing 3401–3420 of 42,103 · page 171 of 2106