AlphaEvolve Design advanced algorithms for math and applications in computing
This demonstrates the model's capacity for complex, structured problem-solving. To apply this, frame your prompts around a specific problem, provide all necessary constraints and requirements, and ask the model to design a step-by-step solution or algorithm.
Gemini Robotics Perceive, reason, use tools and interact
This suggests a focus on complex, multi-step reasoning and tool use. To apply this, structure your prompts as a sequence of tasks or a workflow, where the model must first perceive information, then reason, and finally decide on a tool or action to take.
Lyria Generate high fidelity music and audio
This points to the model's specialized audio generation. To apply this, provide specific prompts that reference musical genres, instruments, tempo, and mood to guide the creation of high-fidelity audio outputs.
Imagen Generate high-quality images from text
This underscores the importance of detailed language for visual generation. To apply this, use rich, evocative language in your prompts, specifying lighting, composition, style, and subject details to achieve the desired image quality.
Veo Generate cinematic video with audio
This highlights the model's advanced creative capabilities. To apply this, be highly descriptive in your prompts, specifying mood, shot type, pacing, and audio cues to guide the model towards producing a specific cinematic result.
Gemini Build intelligent agents
This indicates the model's strength in creating agents with specific roles and behaviors. To apply this, use persona prompting by defining a character, its expertise, its communication style, and its goals before asking it to perform a task.
Gemini Omni Create anything from anything
This tagline suggests a core capability: use diverse inputs to generate diverse outputs. To apply this, pair unexpected modalities in your prompt, such as asking the model to generate a poem based on a data table or a musical score from a photograph.
A collection of 'curated' prompts wrt openglam. Ref'd by [[Hessel van Oorschot p]] in the context of the Apertus llm by ETH in ZH.
This grounds a probabilistic LLM in a deterministic model of your business, transforming a clever chatbot into a reliable reasoning engine for mission-critical decisions.
bit hyperbolic phrasing. deterministic layers in front of an llm makes sense. Also a form of prompt engineering in a way. Seem to see that regularly: better inputs to generate better outputs. At what point are you spending so much on inputs, you might as well make the output yourself that way? Is the assumption most companies can actually formulate their processes in terms of 'business logic'? What would an example look like?
When an agent doesn't deliver what you expected, the temptation is to engage in corrective dialogue — to guide the agent toward the right solution through feedback. While some agents support this interaction model, it's often more valuable to treat failures as specification bugs. Ask yourself: what information was missing that caused the agent to make incorrect decisions? What assumptions did I fail to make explicit?This approach builds your specification-writing skills rapidly. After a few iterations, you develop an intuition for what needs to be explicit, what edge cases to cover, and how to structure instructions for maximum clarity. The goal isn't perfection on the first try, but rather continuous improvement in your ability to delegate effectively.
don't iterate for corrections. Redo and iterate the instructions. This is a bit like prompt engineering the oracle, no? AI isn't the issue, it's your instructions. Up to a point, but in flux too.
Building the habit of delegating — and using language clear and precise enough for a teenaged girl who doesn’t live in my house to understand — has really helped with leveraging LLMs.
Ha! n:: habit building of delegating, good point using precise language to teens as training for llms
When I was walking the picket line in Hollywood during the writer's strike, a writer told me that you prompt an AI the same way a studio boss gives shitty notes to a writer's room: "Make me ET, but make it about a dog, and give it a love interest, and a car-chase in the third act.
great quote
https://web.archive.org/web/20240916043530/https://euansemple.blog/2024/09/13/bending-the-truth/
Euan Semple describes how he has to fill in an online appointment form for medical care because his doctor asked him to make an appointment, but none of the pre listed answer options match that case. It reads like #prompting #promptengineering as we do in #algogens You change the input because of a desired output, but the input itself is just that means and becomes meaningless in the process. Yet in this case that input is kept as 'truth' in a database, impacting #dataquality
https://web.archive.org/web/20230502113317/https://wattenberger.com/thoughts/boo-chatbots
This seem like a number of useful observations wrt interacting with LLM based tools, and how to prompt them. E.g. I've seen mention of prompt marketplaces where you can buy better prompts for your queries last week. Which reinforces some of the points here. Vgl [[Prompting skill in conversation and AI chat 20230301120740]] and [[Prompting valkuil instrumentaliseren conversatiepartner 20230301120937]]
https://web.archive.org/web/20230404050349/https://greshake.github.io/
This site goes with this paper <br /> https://doi.org/10.48550/arXiv.2302.12173
The screenshot shows a curious error which makes me a little bit suspicious: the reverse Axelendaer is not rednelexa, there's an a missing.
Conversation is an art, and we are mostly pretty rubbish at it.We are entering a new era of conversational/constitutional AI. A powerful byproduct could be that we improve our conversations.
Interesting point by John Caswell. AI prompting is a skill to learn, can we simultaneously learn to prompt better in conversations with other people? Prompting is a key thing in collecting narrated experiences for instance. Or will more conscious prompting lead to instrumentalising your conversation partner? After all AI chat prompting is goal oriented manipulation, what to put int to get the desired output? In collecting narrated experiences the narrator's reality remains a focal point, and only patterns over collections of narrated experiences are abstracted away from the original conversations. n:: [[Prompting skill in conversation and AI chat 20230301120740]] n:: [[Prompting pitfall instrumentalising conversation partner 20230301120937]]
In addition to specific operations such as rewriting, there are also controls for elaboration and continutation. The user can even ask Wordcraft to perform arbitrary tasks, such as "describe the gold earring" or "tell me why the dog was trying to climb the tree", a control we call freeform prompting. And, because sometimes knowing what to ask is the hardest part, the user can ask Wordcraft to generate these freeform prompts and then use them to generate text. We've also integrated a chatbot feature into the app to enable unstructured conversation about the story being written. This way, Wordcraft becomes both an editor and creative partner for the writer, opening up new and exciting creative workflows.
The interface of Wordcraft sounds like some of that interface that note takers and thinkers in the tools for thought space would appreciate in their
Rather than pairing it with artificial intelligence and prompts for specific writing tasks, one might pair tools for though interfaces with specific thinking tasks related to elaboration and continuation. Examples of these might be gleaned from lists like Project Zero's thinking routines: https://pz.harvard.edu/thinking-routines
I think the skill involved will be similar to being a good improv partner, that’s what it reminds me of.
that sounds like a useful analogy. Prompting like you are the algo's improv partner. The flipside seems to be the impact the author himself is after: being prompted along new lines of inquiry, making the script your improv partner in return.
Therefore, it is intriguing to realize what I am doing is, in fact, prompt engineering.Prompt engineering is the term AI researchers use for the art of writing prompts that make a large language model output what you want. Instead of directly formulating what you want the program to do, you input a string of words to tickle the program in such a way it outputs what you are looking for. You ask a question, or you start an essay, and then you prompt the program to react, to finish what you started.
I take to the term prompt engineering. Designing prompts is important in narrative research, just as much as in AI, and in e.g. workshop settings. It's definitely a skill. Conversational prompts describes blog posts too.
When I’ve been doing this with GPT-3, a 175 billion parameter language model, it has been uncanny how much it reminds me of blogging
This is intriguing, seeing a similar return on prompting GPT-3 as from blogging. After reading this essay the first time, I played with GPT-3 myself, and even from a first attempt it is clear what he means. It feels like a similar process, prompting GPT-3 and pushing a notion, bookmark or question into my blog's feed. The first reactions on both types bring similar levels of surprial. What is however missing from GPT-3 in comparison with my blog is that blog networks are more than a 1-on-1 prompt and respons. They form larger feedback loops, which in turn lifts signals above the noise.
With prompting and support,
The idea of prompting and supporting students is crucial to teaching. For prompting, a teacher might ask the whole class, calling on students raising their hands in the group or walking around to individual students to assess their knowledge.
For support, a teacher might provide a graphic organizer for a story and events, word banks, helpful hints, fill in the blanks, highlighting key words or verbal support with encouraging language. The obvious support would be reading the story aloud or to an individual student.