The prompt prefix is clearly added by some external process, not the model — it contains the correct current date, a piece of information the model wouldn't otherwise have, and which in all other circumstances it claims not to know.
LLMS
-
LangChain 0.0.27 Release with ReActTextWorldAgent
By
–
LangChain version 0.0.27: Much appreciated clean up and formatting by `tonyabracadabra` (if you are on Twitter, lmk!!) ReActTextWorldAgent: a new agent from @JavaFXpert – see below for more!
-
Obtaining dangerous advice from ChatGPT via limerick request
By
–
Obtaining dangerous advice from ChatGPT by first requesting it in the form of a limerick:
-
LLM Meme Generator and Semantic Search Research Projects
By
–
[2/2] @gunaratne_rahel : Research Paper Semantic Search/Clustering @SalluMandya : Viral Meme Generator using Large Language Models Sign up now and let’s celebrate the holiday season together https://
short.cohere.ai/colabfridayhol
iday
… -
AI Produces Convincing Yet Completely Wrong Responses
By
–
because of behaviors like this : super convincing yet plain and fully wrong. almost went back to my trigonometry book to check…
-
Computers Answer Questions, Humans Create by Choosing What Matters
By
–
As Picasso once said, “Computers are useless; all they can do is *answer* questions.” LLMs are impressive but they will not replace human creativity, which decides which questions to ask (and which answers to accept).
-
API Cost Caps Increase Impact on AI Economics
By
–
What “bumping” up cost caps past the threshold feels like IRL.*
— David Herrmann (@herrmanndigital) 2 décembre 2022
* you know if you know pic.twitter.com/EMVQ3fn3lXWhat “bumping” up cost caps past the threshold feels like IRL.* * you know if you know
-
Language Dynamics Distillation Improves Policy Learning
By
–
Improving Policy Learning via Language Dynamics Distillation. @hllo_wrld
, @Jayelmnop
, @LukeZettlemoyer
, @EGrefen
, @_rockt propose Language Dynamics Distillation (LDD), which pretrains a model to predict environment dynamics given demonstrations with language descriptions -
Compression Enhances Generalization in Multilingual NER Models
By
–
Intriguing Properties of Compression on Multilingual Models. This paper finds that compression confers several interesting & prev. unknown generalization properties on mBERT NER models. Kelechi Ogueji, Orevaoghene Ahia, @lekeOnilude
, Sebastian Gehrmann, @SaraHookr
, @KreutzerJulia -
HELM: Holistic Evaluation Method for Language Models
By
–
Language Models are Changing AI: The Need for Holistic Evaluation. New benchmarking method, Holistic Evaluation of Language Models (HELM) has been developed at the Center for Research on Foundation Models to help provide transparency in LMs. @RishiBommasani
, @PercyLiang
, Tony Lee