alt Hacker NewsWhy this post is here in the front page? The Qwen vector steering performed was a very selective operation that interested only specific layers and weights set, it is non trivial to identify and fix. This is remarkable. Also Experiment 3: no access to forward pass, so why here this post says the contrary of what the paper shows and everybody upvoted it? I don't understand.
Replies
> Why this post is here in the front page?
You know exactly why... because anti-AI hysteria is quite popular on HN.
Any "critique" or "appeal to resist AI" rooted in emotion and inability to admit that intelligence is not a feat unique to humans anymore will make the rounds here.
If people have programmed programs to interpret neural networks, what is so special about the AI doing so? It's a forgone conclusion.
You can let the AI generate training code for the next architecture too.
It's not like the AI is randomly losing its ability to write software just because it involves AI.
I am growing increasingly fond of the term "anti-AI psychosis". It's getting ridiculous sometimes.
Experiment 3 doesn't involve reading the weights in as part of the prompt. It's a coding exercise. Here are the turns: https://github.com/RikiyaT/lm_understand-logs/tree/main/exp3...
At each point the model has to write code to read the weights in with Python and some other Python code to perform analysis, like this: https://github.com/RikiyaT/lm_understand-logs/blob/main/exp3...
My complaint is that the post presents a confusing mix of experiments that imply capabilities that are more than the sum of their parts. This experiment 3 has nothing to do with experiment 1 for instance. In experiment 1 the model does read in the raw weights like it's reading an image.