Like how the brain was understood by its clinical failures, in LLM hallucinations we see bare the true causal mechanisms that lead to its answers. What we mistook for human-like cognition is revealed as something more alien:
LLMS
-
Introducing the ‘LGTM Effect’ for AI-Generated Content Errors
By
–
Starting a campaign to rebrand automation bias as “the LGTM effect”. The LGTM effect: The unshakable tendency of humans to read the first 15% of LLM-generated prose or code, think “lgtm!”, and commit/publish/tweet something that is wrong/batshit-insane/unfunny, respectively.
-
Prompt Engineering Techniques for Instruct-Tuned GPT-3 Models
By
–
For instruct-tuned GPT-3: “You” is automatic transmission, “The following is…” is stick-shift. Second-person imperative makes it emit a single answer and stop. If you pretend you’re writing a document, completions ramble on and you need to plan stop sequences.
-
Artificial Intelligence Enters New Era of Vision and Language
By
–
‘Learning to see and learning to read’: #ArtificialIntelligence enters a new era https://
princeton.edu/news/2023/01/0
3/learning-see-and-learning-read-artificial-intelligence-enters-new-era
… @Princeton #AI #MachineLearning #DataScience #IoT #100DaysofCode #womenwhocode #serverless @enilev @FmFrancoise @Shi4Tech @anijov #NLP #BigData #Analytics #DeepLearning -
Discovering ChatGPT and Enjoying the Experience
By
–
Really appreciate that Nathan. Having the time of my life discovering all this stuff about ChatGPT.
-
ChatGPT’s Creative Poetry Writing Capabilities Impress Users
By
–
The poem one is kind of amazing, actually. It gets very creative. Definitely others should ask ChatGPT to write random poems about stuff.
-
Clarification on hours spent with various language models and AI tools
By
–
Sorry, I mis-spoke in that tweet. Not hundreds of hours with ChatGPT specifically. 750 hours at least with GPT-2, GPT-3, plus a bunch of lesser known large language models and their various modules. Another 250 hours at least with AI art tools as well.
-
Long experience with AI tools since GPT-2 era
By
–
I've been working with AI tools since GPT-2 over 4 years ago at this point I think
-
Prompt Engineering vs. Logit Bias: Understanding ‘Very’ in AI Prompts
By
–
The addition of “very” is the prompt engineering, not the logit bias stuff. If you’re saying use of logit bias disqualifies “very” from counting as prompt engineering I don’t see how.