Are they really such a big RAM buyer?
1,732 karma · joined April 21, 2021
Are they really such a big RAM buyer?
I've never hit the quota on Codex.
On Claude (Code), I used to hit it every other day before switching to Codex.
If you run GrapheneOS, LineageOS or whatever, then it's not real Android, and the entire problem of your OS restricting you from installing apps does not exist.
Not if you count all the energy that was necessary to feed, shelter and keep the the human at his preferred temperature so that he can sit in front of a computer and solve the problem.
The worst offenders are brake sounds not correlating to the car movement, engine sounds not correlating to the car's acceleration, nonsensical car deceleration while braking, and steering wheel not correlating to car steering.
For example, at some point I grew very tired of the superficiality of the questions that Lex Friedman asks his very technical guests. He seems to be more interested into taking the conversation into a philosophy freshman's essay about technology instead of talking about technology itself.
Hearing the Dwarkesh podcast was a breath of fresh air in that regard.
It was a generational leap if there ever has been one. Much bigger than 3.5 to 4.
Even if the code generated by Claude is slightly better, with GPT, I can send as many requests as I want and have no fear or running into any limit, so I feel free to experiment and screw up if necessary.
If LLMs actually hit a plateau, then investment will flow towards other architectures.
Stoicism doesn't tell you to just learn to live with things that you can change. That's only for things that you cannot change.