Re:Claude Sonnet 4 now supports 1M tokens of context
by jbs789 on Wednesday August 13, 2025 @02:15AM
(#44885156)
I'm not sure the idea that a developer maintains a high level understanding is all that controversial...
Re:Claude Sonnet 4 now supports 1M tokens of context
by animuchan on Wednesday August 13, 2025 @02:59AM
(#44885396)
The trend for this idea's controversiality is shown on this very small chart: /
Re:Claude Sonnet 4 now supports 1M tokens of context
by fnordsensei on Wednesday August 13, 2025 @02:08AM
(#44885107)
The brain can literally not process any piece of information without being changed by the act of processing it. Neuronal pathways are constantly being reinforced or weakened.
Even remembering alters the memory being recalled, entirely unlike how computers work.
Re:Claude Sonnet 4 now supports 1M tokens of context
by johnisgood on Wednesday August 13, 2025 @04:27AM
(#44885895)
For humans, remembering strengthens that memory, even if it is dead wrong.
Re:Claude Sonnet 4 now supports 1M tokens of context
by Lutger on Wednesday August 13, 2025 @04:39AM
(#44886002)
I've always find it interesting that once I take a wrong turn finding my way through the city and I'm not deliberate about remembering this was, in fact, a mistake, I am more prone to taking the same wrong turn again the next time.
Re:Claude Sonnet 4 now supports 1M tokens of context
by dberge on Wednesday August 13, 2025 @05:53AM
(#44886490)
> once I take a wrong turn finding my way through the city... I am more prone to taking the same wrong turn again
You may want to stay home then to avoid getting lost.
Re:Claude Sonnet 4 now supports 1M tokens of context
by ehnto on Wednesday August 13, 2025 @02:54AM
(#44885363)
I never intended to say it was true of all codebases for all developers, that would make no sense. I don't know all developers.
I think it's objectively true that the information is not in the LLM. It did not have all codebases to train with, and they do not (immediately) retrain on the codebases they encounter through usage.
All 3 points (you have had all of it your head at some point, it is still there, that is not true of an LLM) are mere conjectures, and not provable at this time, certainly not in the general case. You may be able to show this of some codebases for some developers and for some LLMs, but not all.