It is a surprise that you can move very complex prompts (like pages of text) from Claude 3 to GPT-4 to Gemini 1.5 and have it generally work quite well without modification. Tweaking is usually only a couple of minutes to match the models "mood." I wouldn't have expected that.
@emollick
-
GPT-4.5/5 and Llama-3 capabilities coming soon
By
–
We won’t have wait long: GPT-4.5/5 will help answer 1 & 3. Llama-3 will answer 2
-
Three Critical Questions Shaping AI’s Future Landscape
By
–
This chart shows the three big questions of AI right now (even given the limitations of MMLU as a test):
1) OpenAI was very far ahead, now it isn’t. Will GPT-5 be another leap?
2) Will open source models converge with closed source?
3) Will rapid progress continue or hit a wall? -
GPT-4 Writing Academic Papers Matches Human Quality Study
By
–
Why searching for "delve" in scientific papers is missing the point: this small study shows that other academics consider GPT-4's introductions to papers at least equal to those written by humans As long as the researchers are responsible for the output, AI writing may be a help
-
LLM Generative Capacity and Idea Diversity with Right Prompts
By
–
I think we need to balance this intuition with the fact that LLMs can also be highly generative & even novel. Our paper shows that, with the right prompts, idea diversity from LLMs is high: https://
papers.ssrn.com/sol3/papers.cf
m?abstract_id=4708466
… Or from an esoteric perspective, take: https://
dreams-of-an-electric-mind.webflow.io -
Redefining AI Reasoning: Beyond Human Analogies and Expectations
By
–
I am not saying you are wrong to expect that this should work, but my intuition is strongly that of course it wouldn't. I think words like "reasoning" aren't precise enough when dealing with AI – it can't mean what it does for a human, so what is the expectation?
-
Can LLMs perform tasks without external tools?
By
–
Is this something we would expect an LLM to do without tools?
-
Writing Accessible AI Guide Inspired by Being Digital
By
–
An inspiration for my book was Negroponte’s “Being Digital.” I read it in college and it led me to MIT & the Media Lab. I wanted to write something that was a similar accessible & research-backed introduction to what AI actually can do for us right now.
-
Causal Inference Expert Mixtape Resource for AI Research
By
–
One of the authors is @causalinf
, who was is an expert in thinking about causality. https://
mixtape.scunning.com -
GPT-4 Predicts Future Events Accurately Through Narrative Storytelling
By
–
Not 100% sure what to make of this timey-wimey paper showing GPT-4 is able to predict the future quite accurately (or, after least make guesses about events that happen after its training cut-off) but only when asked to tell stories about what will happen. https://
arxiv.org/abs/2404.07396