I’m frequently pleasantly surprised how well ChatGPT works as a “my quirky shorthand” whisperer.
PROMPT ENGINEERING
-
Reducing LLM Hallucinations Through Confidence Detection
By
–
Why Hallucinations happen with LLMs?
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 27 novembre 2023
Paige Bailey discusses how language models are less likely to have hallucination. She also covers a nice approach where models are able to spot when it has low confidence in answering the question or ask follow up question to ensure… pic.twitter.com/eLzhVZ4TBYWhy Hallucinations happen with LLMs? Paige Bailey discusses how language models are less likely to have hallucination. She also covers a nice approach where models are able to spot when it has low confidence in answering the question or ask follow up question to ensure
-
Filter only applies to Playground, use API directly with curl or Python
By
–
I think that filter only applies to Playground. Your prompt should work if you call the API directly with curl or Python.
-
ChatGPT Reveals Hidden Prompts in DALL-E Bake-Off Competition
By
–
Interestingly if you straight-up tell ChatGPT you’re running a bake-off it will helpfully tell you otherwise elided prompt words to DALL-E.
-
ChatGPT and MidJourney for Creative Writing Workflow
By
–
I’ve also very casually experimented with ChatGPT -> MidJourney. Helps with writer’s block, though has not allowed me to get transformationally better output than MJ out of the box.
-
Create AI Process Tutorials: What Should I Break Down?
By
–
I've been so caught up in sharing all the crazy AI news lately that I haven't made a tutorial in a while. I want to create some killer AI tutorials. Any suggestions on AI processes that you'd love to see broken down step-by-step?
-
Deliberate delay design for AI comfort user experience
By
–
ways to get it faster but actually some of the delay is deliberate for comfort — the chime sound is actually when we are done listening
-
High Resolution Video Generation: Coherency and Noise Parameter Optimization
By
–
On higher resolution videos I've found:
— fofr (@fofrAI) 26 novembre 2023
– coherency takes a hit and there's more warping
– you need lower noise values, like cond_aug 0.01 rather than 0.02
This one was generated at 1792 × 1024 and you can see the warping in the foreground. But I love the rotating planet.
2/2 pic.twitter.com/5gqTc8J8tkOn higher resolution videos I've found: – coherency takes a hit and there's more warping
– you need lower noise values, like cond_aug 0.01 rather than 0.02 This one was generated at 1792 × 1024 and you can see the warping in the foreground. But I love the rotating planet. 2/2 -
Teaching Small Language Models Reasoning Techniques
By
–
5/ Teaching Small LMs To Reason – an approach to teach smaller language models to reason; specifically, the LM is thought to use reasoning techniques, such as step-by-step processing, recall-then-generate, recall-reason-generate, extract-generate,…
-
System 2 Attention: LLM Reasoning for Selective Context Processing
By
–
1/ System 2 Attention – leverages the reasoning capabilities of LLMs to decide what to attend to; it regenerates input context to only include relevant portions before attending to the regenerated context to elicit the final response from the model.