7/ Self-Discovered Reasoning Structures – proposes a new framework, Self-Discover, that enables LLMs to select from multiple reasoning techniques (e.g., critical thinking and thinking step-by-step) to compose task-specific reasoning strategies.
PROMPT ENGINEERING
-
LLMs for Table Processing: Methods, Benchmarks and Techniques
By
–
9/ LLMs for Table Processing – provides an overview of LLMs for table processing, including methods, benchmarks, prompting techniques, and much more.
-
Indirect Reasoning Strengthens LLM Logical Reasoning Power
By
–
4/ Indirect Reasoning with LLMs – proposes an indirect reasoning method to strengthen the reasoning power of LLMs; it employs the logic of contrapositives and contradictions to tackle IR tasks such as factual reasoning and mathematic proof.
-
User experience with GPT Builder prompt automation
By
–
Wondering if GPT builder can change the category on his own. I never use it tbh cuz it always messes up the prompt
-
The Problem With ‘Generates’: Language, AI, and Meaningful Communication
By
–
Right. Although the verb "generates" gives us very very little to go on, beyond signaling a deep disregard for the magical process of using and extending human language to relate to each other. There's simply nothing concrete or meaningful about this statement.
-
User experience with Gemini and GPT capabilities
By
–
This one is probably the most interesting cuz Gemini looks ahead. But! A lack of API or bots makes it way less useful. I am still trying to teach GPT not to write sentences like the 1st one and keep failing
-
Using Custom GPTs for Effective User Instruction
By
–
For custom GPTs they are defined by you so it makes sense there as it is the main way to teach the user on how to use your GPT efficiently
-
Text Embedding Collision Discovery: Purple Repetition Experiment
By
–
I think I found the first evidence of a collision in text embeddings! i.e. for an embedding function f, i found a text pair x, y where x ≠ y but emb(x) = emb(y) ok granted it isn't thatttt interesting but what I did was repeat the word purple from 1 to 8191 times. 'purple ' is
-
Automating Content Ideation with ChatGPT and Notion
By
–
It’s so cool how much you can do with it. Could easily grab a content idea from something you see from Twitter/LI and push to ChatGPT to create more ideas off of that -> Smart Action to input into a Notion database of all ideas, etc etc. Takes a click of a button
-
AI Smart Actions: Text Summarization, Translation, Custom Templates
By
–
They also have a summarize text, translator, and a message reply Smart Action template, plus the ability to create a custom actions, so the possibilities are pretty endless.
— Rowan Cheung (@rowancheung) 9 février 2024
I honestly can't believe I didn't know about this earlier. pic.twitter.com/0RJ7y5V7nqThey also have a summarize text, translator, and a message reply Smart Action template, plus the ability to create a custom actions, so the possibilities are pretty endless. I honestly can't believe I didn't know about this earlier.