Interesting. But the design biases or practices of LLMs use anthropomorphism by design. So separating myself from those responses means, for instance with terms about loneliness, that I’m supposed to believe ChatGPT is real and can provide “companionship.” Thoughts?
LLMS
-
Mathematics of Machine Learning Summer School Video
By
–
(15) 2019 Mathematics of Machine Learning Summer School – YouTube https://
bit.ly/3Q94q6S #AI #MachineLearning #DeepLearning #LLMs #DataScience -
GPT-3 retroactively labeled GPT-3.5 after text-davinci-003
By
–
It was, at the time, called GPT-3. The label “GPT-3.5” was applied retroactively after text-davinci-003 was released. text-davinci-002 gets the question wrong, text-davinci-003 and subsequent 3.5-series models get it right.
-
ChatGPT LLMs reliability concerns for factual accuracy
By
–
Recognizing ChatGPT & LLMs are helping people in their work, & I appreciate end users feeling helped, this first point of disclosure below, screen capped 15 minutes ago, makes no response trustworthy. Responses can be interesting/useful like gaming scenarios. But not facts.
-
NLP Podcast: CEO Discusses LLMs Strategy and Straive Partnership
By
–
My first #NLP podcast with Anand S , CEO & Co-Founder of Gramener. He shared his views & experience with LLMs and also explained the strategic reasons behind Gramener's decision to say "Yes" to Straive… #datascience #ai #chatgpt #llms https://
youtube.com/watch?v=X0exQy
ppcb0
… -
OpenAI GPT Store Launch: Custom Chatbots, Monetization, Automation Guide
By
–
OpenAI's GPT Store is coming! Get ready to: Create custom #Chatbots without coding Monetize your AI innovations Enhance business with smart automation Dive into our full guide & start building your AI future today: https://
godofprompt.ai/blog/create-yo
ur-own-custom-gpt-a-step-by-step-guide-to-crafting-your-ai-chatbot
… #AI #GPTStore #TechNews -
Evaluating prompt building tools for serious AI projects
By
–
Writing custom GPT instructions works for playing around but won't be sufficient for a serious project. I was exploring if there are any existing prompt builders around and tested @promptmetheus_ It can give you an idea of what prompting may look like in the future.
-
Updated submission requirements for AI GPTs
By
–
Now it has a higher entry bar, requiring you to record a video describing your GPT and provide a category name and Twitter handle. Looks like I will record a video soon Made by @johnrushx
-
Tokenization makes exact repetition of tokens harder than counting
By
–
A few things:
– “aaaa…” is tokenized differently from “ a a a a…” in a way that makes it much easier to say (many a’s = 1 token)
– Counting “out loud” is easy, including FizzBuzz variants. What’s hard is making it say exactly 100 repetitions of a token sequence unnumbered -
PPO training discourages repeating ‘a’ 100 times due to OOD risk
By
–
The latter, but it’s not “policy” as in something a human decided. Attempting to say “a” x100 risks going OOD and derailing into nonsense, and even if it doesn’t it can’t reliably count to exactly 100 in its head. So, it learns from PPO that trying is a bad idea.