Saved by Isabelle Levent
Do Prompt-Based Models Really Understand the Meaning of their Prompts?
The problem in this domain is sycophancy.
When you're first learning something, you don't actually know what to look for . You have too many unknown-unknowns, you don't have any wisdom, you have no abstractive connections to make.
The reason LLMs are hazardous during this period, is that they're always going to let you take the lead on everything. Th... See more
When you're first learning something, you don't actually know what to look for . You have too many unknown-unknowns, you don't have any wisdom, you have no abstractive connections to make.
The reason LLMs are hazardous during this period, is that they're always going to let you take the lead on everything. Th... See more
Link
The idea is: learn to prompt chatbots very well = get way better outputs.
Right now, intricate prompting is helpful for some tasks. But over time, we think it’s an overrated skill. Here’s why:
1. As AI models improve, they require less “engineered” prompts. DALL-E 3 is a great example of this (you get top-tier images with < 10-word prompts).
In this c... See more
Right now, intricate prompting is helpful for some tasks. But over time, we think it’s an overrated skill. Here’s why:
1. As AI models improve, they require less “engineered” prompts. DALL-E 3 is a great example of this (you get top-tier images with < 10-word prompts).
In this c... See more
Shortwave — rajhesh.panchanadhan@gmail.com [Gmail alternative]
#4—Prompting is a finicky art, but a worthy investment While it would be great if the three techniques I’ve shared so far immediately transform your prompts, there's a decent chance they will fall flat for your use case. My guess is that they will even become irrelevant as models become smarter and more cost-effective over time. My point in sharing
... See moremail.google.com • Fwd: How I Prompted My Way to Publish-Ready Content - kaustubhs@groww.in - Groww Mail
The community remains puzzled about whether these models genuinely generalize to unseen tasks, or seemingly succeed by memorizing the training data. This paper makes important strides in addressing this question. It constructs a suite of carefully designed counterfactual evaluations, providing fresh insights into the capabilities of state-of-the-ar... See more