Explicitly filter out text that could be harmful or questionable. Can be done in two ways: 1. Simple keyword-based filtering to avoid harmful text as O/p to the end-user.
2. Running it through a content filtering model side-by-side just like the one you see in OpenAI playground.
AI
-
Content Filtering Strategies for Harmful Text Output
By
–
-
Keras Reaches 2.5 Million Users After 8 Years of Growth
By
–
Kind of insane that I've been working on Keras for nearly 8 years and it's still growing at ~30% per year. Never thought it would ever get to 1M users, much less the ~2.5M users we have currently (and growing)
-
Gut Microbiota Could Prevent Alzheimer’s Disease Progression
By
–
"These exciting results highlight the potential to harness the gut microbiota to prevent or slow the progression of AD and other tauopathies and raise awareness about the potential long-term effects of early-life diet" https://
science.org/doi/10.1126/sc
ience.adf9548
… @Tan_ee_Ya @YuemingLiLab -
Google’s Revolutionary New Translation Feature
By
–
When Google's new translate feature is a game-changer. (credit: http://
bit.ly/2FOvtT4) -
Generating Kanji Images from English Text
By
–
A related experiment, generating “Kanji” images from English text:
-
Link to copyable prompts available at bottom
By
–
If you look at the bottom you will find a link with all the prompts to copy paste
-
No One Size Fits All: Technology Depends on Your Use Case
By
–
There is no one size fits all, it totally depends on your usecase.
-
Documentation CSS Improvement Enhances Text Output Display
By
–
Improved css on docs site – Albert Avetisian Finally, a small but meaningful change: per a suggestion by Albert, the css has now been updated so that long text outputs are displayed more fully (rather than making it so that you have to scroll)
-
LangChain Adds Custom Prompt Support for LLMBash API QAEval
By
–
Custom prompts for LLMBash, API, and QAEval chains – @nickscamara_ Francisco Ingham Continuing the trend from yesterday, more chains now have the ability to pass in custom prompts! LLMBash: https://
langchain.readthedocs.io/en/latest/modu
les/chains/examples/llm_bash.html#customize-prompt
… QAEval: https://
langchain.readthedocs.io/en/latest/use_
cases/evaluation/question_answering.html#customize-prompt
… -
LangChain v0.0.63 Releases Enhanced Parameters and Custom Prompts
By
–
v0.0.63 Expose more @serp_api parameters – h/t @kweyamba_ai
Custom prompts for LLMBash, API, and QAEval chains – @nickscamara_ Francisco Ingham
Improved css on docs site – h/t Albert Avetisian