News for hackers. Stuff that matters.
Re:GPT‑5.3‑Codex‑Spark by moralestapia on Thursday February 12, 2026 @02:58PM (#46994230)
This comment doesn't make sense.
Re:GPT‑5.3‑Codex‑Spark by Sohcahtoa82 on Thursday February 12, 2026 @03:26PM (#46994624)
One wafer will turn into multiple chips.

Defects are best measured on a per-wafer basis, not per-chip. So if if your chips are huge and you can only put 4 chips on a wafer, 1 defect can cut your yield by 25%. If they're smaller and you fit 100 chips on a wafer, then 1 defect on the wafer is only cutting yield by 1%. Of course, there's more to this when you start reading about "binning", fusing off cores, etc.

There's plenty of information out there about how CPU manufacturing works, why defects happen, and how they're handled. Suffice to say, the comment makes perfect sense.

Re:GPT‑5.3‑Codex‑Spark by snovv_crash on Thursday February 12, 2026 @04:17PM (#46995306)
That's why you typically fuse off defective sub-units and just have a slightly slower chip. GPU and CPU manufacturers have done this for at least 15 years now, that I'm aware of.
Re:GPT‑5.3‑Codex‑Spark by azinman2 on Thursday February 12, 2026 @03:03PM (#46994315)
Sure it does. If it’s many small dies on a wafer, then imperfections don’t ruin the entire batch; you just bin those components. If the entire wafer is a single die, you have much less tolerance for errors.
Re:GPT‑5.3‑Codex‑Spark by dekhn on Thursday February 12, 2026 @03:19PM (#46994539)
Although, IIUC, Cerebras expects some amount of imperfection and can adjust the hardware (or maybe the software) to avoid those components after they're detected. https://www.cerebras.ai/blog/100x-defect-tolerance-how-cereb...
Re:GPT‑5.3‑Codex‑Spark by pertymcpert on Thursday February 12, 2026 @03:26PM (#46994626)
You can just do dynamic binning.
Re:GPT‑5.3‑Codex‑Spark by DocJade on Thursday February 12, 2026 @03:01PM (#46994284)
Bigger chip = more surface area = higher chance for somewhere in the chip to have a manufacturing defect

Yields on silicon are great, but not perfect

Re:GPT‑5.3‑Codex‑Spark by moralestapia on Thursday February 12, 2026 @03:45PM (#46994880)
Does that mean smaller chips are made from smaller wafers?
Re:GPT‑5.3‑Codex‑Spark by Sohcahtoa82 on Thursday February 12, 2026 @05:55PM (#46996457)
Nope. They use the same size wafers and then just put more chips on a wafer.
Re:GPT‑5.3‑Codex‑Spark by moralestapia on Thursday February 12, 2026 @06:15PM (#46996649)
So, does a wafer with a huge chip has more defects per area than a wafer with 100s of small chips?
Re:GPT‑5.3‑Codex‑Spark by dgfl on Thursday February 12, 2026 @06:34PM (#46996819)
There’s an expected amount of defects per wafer. If a chip has a defect, then it is lost (simplification). A wafer with 100 chips may lose 10 to defects, giving a yield of 90%. The same wafer but with 1000 smaller chips would still have lost only 10 of them, giving 99% yield.
Re:GPT‑5.3‑Codex‑Spark by moralestapia on Friday February 13, 2026 @01:16AM (#46999503)
As another comment referenced in this thread states, Cerebras seems to have solved by making their big chip a lot of much smaller cores that can be disposed of if they have errors.
Re:GPT‑5.3‑Codex‑Spark by dgfl on Friday February 13, 2026 @02:31AM (#46999947)
Indeed, the original comment you replied to actually made no sense in this case. But there seemed to be some confusion in the thread, so I tried to clear that up. I hope I’ll get to talk with one of the cerebras engineers one day, that chip is really one of a kind.
Re:GPT‑5.3‑Codex‑Spark by moralestapia on Friday February 13, 2026 @07:59AM (#47002229)
Yes, amazing tech. You should join their Discord, it's pretty active these days!
Re:GPT‑5.3‑Codex‑Spark by wat10000 on Thursday February 12, 2026 @07:56PM (#46997536)
They can be made from large wafers. A defect typically breaks whatever chip it's on, so one defect on a large wafer filled with many small chips will still just break one chip of the many on the wafer. If your chips are bigger, one defect still takes out a chip, but now you've lost more of the wafer area because the chip is bigger. So you get a super-linear scaling of loss from defects as the chips get bigger.

With careful design, you can tolerate some defects. A multi-core CPU might have the ability to disable a core that's affected by a defect, and then it can be sold as a different SKU with a lower core count. Cerebras uses an extreme version of this, where the wafer is divided up into about a million cores, and a routing system that can bypass defective cores.

They have a nice article about it here: https://www.cerebras.ai/blog/100x-defect-tolerance-how-cereb...

Re:GPT‑5.3‑Codex‑Spark by louiereederson on Thursday February 12, 2026 @05:31PM (#46996220)
You say this with such confidence and then ask if smaller chips require smaller wafers.