google is broken...
-
amazing how jank this all is
@liaizon Perfect comedy! Really digging the references on this one:
-
@liaizon Perfect comedy! Really digging the references on this one:
@despens its amazing to see how everytime google uses citations they are basically randomly added later. like it makes up some shit, then "cites" it by just showing a link that contains a single word of your search.
-
@despens its amazing to see how everytime google uses citations they are basically randomly added later. like it makes up some shit, then "cites" it by just showing a link that contains a single word of your search.
@liaizon
This post of yours is actually a prompt that forms the foundation of a billion dollar business -
amazing how jank this all is
@liaizon
The correct answer is 3.
"Rassemblement National" -
amazing how jank this all is
@liaizon missed opportunity, Google, missed opportunity.
-
@liaizon missed opportunity, Google, missed opportunity.
@fluchtkapsel its impressive how consistent this "bug" is, like they have to realize it by now. I wonder what the internal Google chat looksike atm
-
amazing how jank this all is
someone at google is still alive!
-
someone at google is still alive!
@liaizon
the sad thing is that they can (and might) fix this, but the fix will be one of these two:1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat. -
@liaizon
the sad thing is that they can (and might) fix this, but the fix will be one of these two:1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat.@s_ol it should be doing tool calls anyway for many questions. Like Google search used to do basic math and equations inline without searching.
-
@liaizon
the sad thing is that they can (and might) fix this, but the fix will be one of these two:1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat.@liaizon
i was under the impression that other general-purpose models have solved this and would've guessed they implemented option 2 but actually chatgpt is still confidently wrong (now with sources!)
-
@liaizon
i was under the impression that other general-purpose models have solved this and would've guessed they implemented option 2 but actually chatgpt is still confidently wrong (now with sources!)@s_ol I love how all these companies are completely ruining the concept of souces and citations
-
@liaizon
the sad thing is that they can (and might) fix this, but the fix will be one of these two:1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat. -
-
D dantescanline@autonomous.zone shared this topic
