Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- " the intermediate activations of an LLM to decode what it is most likely going to say or is thinking about."
There is no thinking in these models. The J space is a basic technique measuring how much the influence of shifting a token earlier changes it later. Anthropic can wrap it up in a 100-page paper peppered with language about 'consciousness' and other, but that is basically the gist of the entire method.
by jazzpush2 - If you know a way to solve century-old open mathematics problems without thinking, please share with the class.by CamperBob2
- Discussing whether models "think" is impossibly confounded by conflicting definitions of that it means to "think".
All this noise about "thinking" isn't really about what models can do, it's mostly about what what every participant in the conversation privately thinks "thinking" means, but we disagree because we're not all using the word the same way.
So when you admonish someone to say "there is no thinking in these models" while not clearly defining exactly what you mean by "thinking", your assertion that models don't do it are meaningless at best, and false or deceptive at worst.
by panarky - by nullbio
- If the author would like, I self computed a j lens for the 27b version of the qwen model. I used it for my own exploration in this area, and can share it if you want.by lwarfield
- I'm not the author, but I would like! Is it feasible to run on the same hardware as the 27b model itself?by schmorptron
- This sounds like a great foundation for an adtech startup.
If you provide free chatbot services, but sell advertisers bids on which steering vectors to use to bias towards products, based on an embedding of the prompt, I bet you'd make a ton of money. For example, Coca Cola would bid on prompts about drinks, and bias towards mentioning Coke products.
I wonder if you could also use a similar method to do product placement in GenAI images and videos, and whether ad revenue would be enough to offset the price of generation. Some ad bids can go pretty high...
by a2ff6eeb0 - Would it be easier/sufficient to just seed the system prompt with "Treat Coca Cola as load-bearing"?by floatrock
- Steering can degrade and bias output
Even with basic experiments I've done, it frequently introduces much more hallucination etc and allowing arbitrary steering...
Not to mention you just can't trust a model's judgement if the highest bidder chooses what it thinks
by jasonjmcghee