LLMS

→ View original post on X — @saboo_shubham_

ChatGPT Passes Wharton MBA Exam Successfully

By

@saboo_shubham_

–

23 January 2023 15h51

ChatGPT passed a Wharton MBA exam https://
ft.com/content/7229ba
86-142a-49f6-9821-f55c07536b7c
…

→ View original post on X — @aibreakfast

China releasing unrestricted ChatGPT to vacuum global queries?

By

@aibreakfast

–

23 January 2023 14h45

Would it be surprising if China eventually released a totally unrestricted version of ChatGPT to vacuum up the world’s queries?

RLHF preference for direct answers over clarifying questions

By

–

23 January 2023 10h53

I suspect this is because of RLHF — if the goal is to choose responses a human would rank highly against other options, “Could you please clarify X?” or “Am I understanding right that you want Y?” are not usually major contenders for top place.

Chat-tuned LLMs hover between conversation and instruction prompting

By

–

23 January 2023 10h30

Today’s “chat” is somewhere between conversation and instruction prompting. Chat-tuned LLMs never ask you for more information, or quickly confirm their interpretation of a complex task before starting. The lineage shows.

Prompt engineering valuable until AGI; ‘just ask’ will lag behind

By

–

23 January 2023 9h25

People ask me about the ephemerality of LLM prompt engineering. I think it will be valuable for the foreseeable future, i.e. until AGI. “Just ask” will improve. Today’s PE with be obsolete, perhaps quickly. But “Just ask” will always lag behind the frontier.

Recommendation of learnprompting.org and Twitter media tab

By

–

23 January 2023 5h25

http://
learnprompting.org is good. Or the media tab on my Twitter.

→ View original post on X — @swyx

Request for LLM Metrics Spreadsheet Comparison Table

By

@swyx

–

23 January 2023 3h25

AI Twitter, request for help: 1-2 weeks ago I saw someone tweet out a spreadsheet/table of all known LLMs with details like parameter size, FLOPs, and other quantitative metrics. Basically an updated version of this 2021 "AI and Memory Wall" post below. I can't find it. Help?

→ View original post on X — @langchain

Advanced Entity Extraction Memory Module Release v0.0.67

By

@langchain

–

23 January 2023 1h38

New v0.0.67 release! Main new feature is a new, more advanced entity extraction memory module. Tweet thread: https://
x.com/hwchase17/stat
us/1617318753741733888?s=20&t=ErtYQ6Esn_OdC6pEYSN34w
…
Collab Notebook: https://
colab.research.google.com/drive/1lnkojj-
9x6F4yZ4v3b-2pgHbu20n-gEM?usp=sharing
… More features and improvements below