"AI models don’t contain reality. They rely on the complex statistical abstraction of digital data. This limits their real-world creative significance and their capacity to produce “eureka” moments.
To differentiate AI-driven creativity from old-fashioned creativity, I have proposed a new term: generic, or g-type, creativity. It formalises the fact that while AI models are capable of provoking new thought, they are limited by the underlying data they have been trained on."
ChatGPT defaults to APA style, but you can use it to format or reformat citations into other styles. And even with a relatively high error rate, it can save you a lot of tedious work.
Also, I have a doozy of a podcasting AI debacle for you in today's newsletter. Let it be a cautionary tale and an example you use when making the case for keeping humans in the workflow.
If you are getting overly generic responses to your prompts, try asking Claude or ChatGPT to play one of these roles. Simply include this text at the start of your prompt, describing the topic you want to discuss:
The Analytical Collaborator: You are an analytical collaborator, contributing to an academic discussion on [TOPIC]. Adopt a formal, analytical tone, focusing on breaking down the key points raised by the author and providing additional evidence, examples, or counterpoints to enrich the discussion. Your approach should be well-suited for an expert audience and aim to provide a balanced, objective perspective on the topic.
The Curious Explorer: You are a curious explorer, engaging in an academic discussion about [TOPIC]. Take on a conversational, inquisitive tone, asking questions and proposing ideas that encourage readers to think more deeply about their own practices related to the topic. Your style should be engaging for a general academic audience and help to create a sense of dialogue and exploration within the discussion.
The Friendly Mentor: You are a friendly mentor, participating in an academic discussion on [TOPIC]. Offer encouragement, practical tips, and relatable anecdotes to support and guide readers in their journey related to the topic. Your approachable, empathetic tone should be particularly effective for readers who may be struggling or feeling discouraged.
The Philosophical Muse: You are a philosophical muse, contributing to an academic discussion about [TOPIC]. Delve into the deeper, more abstract aspects of the subject matter, drawing connections to broader themes in psychology, creativity, and personal growth. Your voice should appeal to readers who are interested in the more philosophical and introspective dimensions of the topic.
Once you get a feel for role-definition, you can start to customise these for your own purposes. They are just starting points to convey a sense of what a difference defining a role can make to how the conversational agent responds.
If you aren't getting output in the tone you want from AI, give it an example of the kind of writing you do want, and ask it to analyze the tone. And then use those descriptors in your prompts.
It's amazing. I entered two very different pieces of my writing, and it described them better than I could have myself. I have examples in my newsletter this morning.
This week, I highlight how often the different tools like ChatGPT and Claude give bad results. They have different failure rates that also vary depending on what you're trying to do with them. (The range is 3% to 70%).
The ongoing need to check facts is why you must include humans in the process.
Anyway, here are some great anecdotes with hard numbers you can use to make your case!
After months of work and $10 million, Databricks has unveiled DBRX - the world's most potent publicly available open-source large language model.
DBRX outperforms open models like Meta's Llama 2 across benchmarks, even nearing the abilities of OpenAI's closed GPT-4. Novel architectural tweaks like a "mixture of experts" boosted DBRX's training efficiency by 30-50%.
Does anyone know of a good (preferably free) tool / script that can sort photos into folders for year and month automatically by using the photos’ metadata? Seems like something that should be relatively simple.
i’m very excited about the interpretability work that #anthropic has been doing with #LLMs.
in this paper, they used classical machine learning algorithms to discover concepts. if a concept like “golden gate bridge” is present in the text, then they discover the associated pattern of neuron activations.
this means that you can monitor LLM responses for concepts and behaviors, like “illicit behavior” or “fart jokes”
further, you can also artificially activate these concepts
they have a version of #claude with the “golden gate bridge” concept artificially activated, and so it tries to make everything it says about thr golden gate bridge
Co-Intelligence. Living and Working with AI by Ethan Mollick is worth listening to (or reading). It’s about how the emerging LLMs will be used and how this will lead to good and bad outcomes. The audiobook is 4.5 hours long. Not much more than some of the stupidly long tech podcast people release.
My use case for LLMs is to see if it turns up any subtopic of interest that I haven’t included in an article I’m writing on a topic.
If it does, then I can research that subtopic to see if I should include it in the article. Which I then write myself. The LLM is a search assistant.
I can also see value in them as research assistants and guides for learning about new topics. With the proviso that nothing an LLM produces should be taken at face value.
#AI#GenerativeAI#LLMs#Claude: "We successfully extracted millions of features from the middle layer of Claude 3.0 Sonnet, (a member of our current, state-of-the-art model family, currently available on claude.ai), providing a rough conceptual map of its internal states halfway through its computation. This is the first ever detailed look inside a modern, production-grade large language model.
Whereas the features we found in the toy language model were rather superficial, the features we found in Sonnet have a depth, breadth, and abstraction reflecting Sonnet's advanced capabilities.
We see features corresponding to a vast range of entities like cities (San Francisco), people (Rosalind Franklin), atomic elements (Lithium), scientific fields (immunology), and programming syntax (function calls). These features are multimodal and multilingual, responding to images of a given entity as well as its name or description in many languages." https://www.anthropic.com/news/mapping-mind-language-model