As ChatGPT and systems like it improve, I worry we’ll forget what hallucination looks like. We’ll forget it’s there, lurking in the distributional tails. And we will commit. And upon our servers will be errors. And we will post. And upon our timelines there will be dunks.
LLMS
-
Prompt Engineering Challenges: Avoiding Unreliability and Confabulation in Text-Davinci-002
By
–
But the unreliability, the confabulation, was unmissable. You can’t use text‑davinci‑002 without seeing it. Learning to avoid it in narrow domains is much of the challenge of prompt engineering.
-
Evolution of LLM Hallucinations and AI Promise
By
–
I began studying LLMs to understand the content of their hallucinations. Even in text‑davinci‑002, confabulation was oxygen. 003 has less. ChatGPT less still. Every year, we need squint less to see promise.
-
LLM Hallucinations Reveal Alien Causal Mechanisms of AI Cognition
By
–
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:
-
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.