Re:Being confidently wrong is the only thing holding AI back
by Workaccount2 on Friday August 22, 2025 @11:27AM
(#44985782)
I'm sure somewhere in the current labs there are teams that are trying to figure out context pruning and compression.
In theory you should be able to get a multiplicative effect on context window size by consolidating context into it's most distilled form.
30,000 tokens of wheel spinning to get the model back on track consolidated to 500 tokens of "We tried A, and it didn't work because XYZ, so avoid A" and kept in recent context
Re:Being confidently wrong is the only thing holding AI back
by traceroute66 on Friday August 22, 2025 @09:46AM
(#44984648)
> No human would keep trying one of the solutions included in the context that are marked as not valid.
Exactly. And certainly not a genius human with the memory of an elephant and a PhD in Physics .... which is what we're constantly told LLMs are. ;-)
Re:Being confidently wrong is the only thing holding AI back
by vidarh on Friday August 22, 2025 @10:49AM
(#44985346)
I agree it shouldn't be a problem, but if you don't regularly run into humans who insist on trying solutions clearly signposted as wrong or not valid, you're far luckier than I am.
Re:Being confidently wrong is the only thing holding AI back
by gavinray on Friday August 22, 2025 @09:56AM
(#44984753)
> No human would keep trying one of the solutions included in the context that are marked as not valid.
While I agree, and also use your work around, I think it stands to reason this shouldn't be a problem. The context had the original problem statement along with several examples of what not to do and yet it keeps repeating those very things instead of coming up with a different solution. No human would keep trying one of the solutions included in the context that are marked as not valid.