[SwellJoe]

I make a point of never going beyond about 220k, unless absolutely necessary (and it's almost never necessary), anyway, even with models that degrade more slowly, so this is just a discount.

[johnbarron]

64k ought to be enough for anybody

[adamtaylor_13]

Why stop there? No true developer needs more than 32k!

--

Jesting aside, I cannot think of a single session in recent memory that used less than ~70k tokens, so I presume you are joking.

[gck1]

Heck, agents don't start editing before they're already at 70k for me.

I've played with explorer agents giving exploration summaries to help the implementer agents use more of their context for implementation, but it doesn't work as well. There's always something lost in the handoff.

[gosub100]

It was from a famous quote supposedly from bill gates in the early days of computing: "640K (RAM) ought to be enough for anybody".

Apparently it was taken out of context or misattributed or something. Similar to "Al Gore said he invented the internet"

[Computer0]

My understanding is that models can suffer “context limit anxiety” and a higher context limit will make it perform better especially as the context expands