I would have more contention with "Dynamic taint", but the paper doesn't appear to be AI slop at all.
As I understand the paper they are saying the reasoning/thinking you see is actually a translation of what is actually going on, and stuff can be lost in the translation. Similar to what was observed in j-space.
With all (a lot?) of this language, it's not that it's using new turns of phrases, it's that it will use the same rare but valid phrases over and over. Everybody has their own speaking patterns. But imagine if one person's idiosyncrasies were everywhere. That's what's happened here.
>" However, various strands of evidence indicate that a"
Strands of evidence? My best guess would be that:
0- this is ai generated slop
1- it's using that watermarking technique
2- it's obviously detectable and degrades quality
3- it's amplified when inferencing on its own content and generates slop
Watermarking doesn't degrade output (this is a provable fact) and it is not detectable by a human reading the text.
I would have more contention with "Dynamic taint", but the paper doesn't appear to be AI slop at all.
As I understand the paper they are saying the reasoning/thinking you see is actually a translation of what is actually going on, and stuff can be lost in the translation. Similar to what was observed in j-space.
Maybe you shouldn't be so quick to jump to conclusions, as "strands of evidence" is not a rare turn of phrase and long predates LLMs
https://ludwig.guru/s/strand+of+evidence
With all (a lot?) of this language, it's not that it's using new turns of phrases, it's that it will use the same rare but valid phrases over and over. Everybody has their own speaking patterns. But imagine if one person's idiosyncrasies were everywhere. That's what's happened here.
1 reply →
if Mickens has fallen and resorted to publishing slop then there is no hope for the rest of us