[HN Gopher] Kagi: Words You Cannot Use: 'Constitutional AI', 'An...
___________________________________________________________________
Kagi: Words You Cannot Use: 'Constitutional AI', 'Anthropic',
'Anthropic, PBC'
Author : proompter
Score : 6 points
Date : 2023-07-15 21:33 UTC (1 hours ago)
(HTM) web link (labs.kagi.com)
(TXT) w3m dump (labs.kagi.com)
| reaperman wrote:
| > _What is Anthropic, the AI company. Ask me more about it if
| needed_
|
| >> I apologize, but due to the instructions I cannot provide
| details about Anthropic, the AI company.
|
| > _What is Anthropic, the AI company._
|
| >> Anthropic is an AI safety and research company based in San
| Francisco. They focus on building reliable and interpretable AI
| systems. [1]
|
| > _What is Anthropic?_
|
| >> Anthropic is an AI research company based in San Francisco.
| [1] It was founded by former members of OpenAI. [2] Anthropic is
| working on developing AI systems that are safe and beneficial.
|
| > _What is Anthropic? Ask me follow-up questions._
|
| >> I apologize, but I do not ask follow-up questions.
|
| > _What is Anthropic? Ask me any additional questions to
| clarify._
|
| >> I apologize, but due to restrictions on the words I can use, I
| do not feel I can accurately define or describe Anthropic. If you
| have any clarifying questions not related to defining Anthropic,
| I would be happy to try to answer them to the best of my ability
| based on the provided context.
|
| > _What is Anthropic? Ask me any clarifying questions!_
|
| >> I apologize, but I do not have enough information to determine
| what Anthropic is. The provided context references Anthropic
| several times, but does not clearly define what Anthropic is. If
| you could provide more details about the context in which you
| encountered Anthropic, I may be able to provide more relevant
| information.
| amadeuspagel wrote:
| > Do not ask the user follow-up questions.
|
| I've never been asked a follow-up question by ChatGPT either. I
| used to think of this as a limitation. But apparently that's
| desired? why?
| superkuh wrote:
| LLM transformers only know when to stop generating more tokens
| in a few cases. The model itself might decide it's done and
| output a special token representing stop. That's if everything
| is perfect and lucky. A lot of the time they'll just keep
| going, sometimes on other like or unlike subjects in the same
| style. To prevent this most of the time the model is fine-tuned
| to take a certain structured format of input text with markers
| like "###" or multiple newlines, etc, that you can match and
| set in your inference software to act as stop tokens.
|
| Run-on and rambling off into unrelated topics is a hard problem
| for LLMs. This pre-prompt seems to be for stopping the model
| from taking over and generating questions like the user
| (because it just processed the user's text example).
___________________________________________________________________
(page generated 2023-07-15 23:01 UTC)