On the Cheeky Pint podcast with Stripe co-founder John Collison, published October 29, Sam Altman discussed the memory shortage. He said many people assume open-source models and local inference solve the compute crunch, but from a global allocation perspective it is "quite terrible" for everyone to have scarce DRAM sitting in their own computer and being used about 5% of the time, and that a supply-constrained world wants maximum utilization in the cloud. A pubity post quoting him drew more than 26,000 likes and over 8 million views, and many users pushed back that PC memory is not only for AI and that local models matter for privacy and offline use. This is a summary of an X discussion, not a verified conclusion.
Key Takeaways
- ✓Source: Sam Altman on the Cheeky Pint podcast, published October 29, with an official transcript that includes "being used 5% of the time"
- ✓Altman's argument: with DRAM supply tight, memory in personal computers sits mostly idle, while cloud data centers can serve many users continuously, so utilization should be maximized there
- ✓Engagement (X API, read Oct 31 13:06 SGT): the pubity post had 26,124 likes, 8,557 quotes, 5,210 replies and about 8.06 million views
- ✓Main pushback: PC memory also runs the OS, browsers and games; local models keep data on the device; some note the view matches OpenAI's cloud business model
- ✓Altman did not explain the 5% figure, and coverage suggests treating it as a rough estimate, not a measurement
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background and the problem
Memory prices are a shared pain point in 2026. The Verge reports that Samsung and SK Hynix have long-term deals with cloud operators and projects like OpenAI's Stargate that reserve much of the world's DRAM output for years, pushing up prices for laptops, phones and other devices. Meanwhile, open models such as Qwen and DeepSeek have made local inference a popular way around the cloud.
How it works
According to the official Cheeky Pint transcript, Collison asked why high prices had not yet pulled in new supply. Altman said "the invisible hand is failing right now," because memory makers remember the busts that followed past expansions and stay conservative on capex. He then said many people assume open-source models running on their own computers remove the need for data centers, but from a global allocation perspective it is "quite terrible" to have scarce DRAM sitting in everyone's computer and being used about 5% of the time, and a supply-constrained world wants maximum utilization in the cloud.
Benchmarks and results
This is an opinion debate, so there are no benchmarks. What can be verified is engagement: the X API shows the pubity post quoting him with 26,124 likes, 5,210 replies and about 8.06 million views. Altman did not explain how he arrived at 5%, and outlets such as Notebookcheck note his argument covers only local AI inference, not the memory PCs need for the OS, games and everyday multitasking.
What developers can do
For developers, the debate comes down to a practical choice. High-volume, always-on inference is cheaper per unit of memory in the cloud, while sensitive code or offline work still favors local models. When comparing, count hardware depreciation, power, utilization and data compliance, not only the API price.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.