
Sam Altman says DRAM capacity should go to data centers, not PCs
In a Cheeky Pint interview, he called home DRAM and local inference quite terrible because memory sits idle most of the time.
6 stories, newest first · one card per story

In a Cheeky Pint interview, he called home DRAM and local inference quite terrible because memory sits idle most of the time.

He argues personal computers leave DRAM idle most of the time while cloud deals, including Stargate, reserve future supply.

He argues cloud utilization is better than local inference and says OpenAI is designing a custom AI chip called Jalapeno.
A collapse theorem says physical separation makes protected executions match the fault-free run for every finite prefix.

Micron and Samsung executives expect the memory shortage to last through 2028 as AI HBM demand exceeds supply.

Micron's CEO says memory supply will be much tighter in 2027 and 2028, with no balance in sight.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views