At first, prompting seemed to be a temporary workaround for getting the most out of large language models. But over time, it's become critical to the way we interact with AI. On the @LightconePod, Garry, Harj, Diana, and Jared break down what they've learned from working with hundreds of founders building with LLMs: why prompting still matters, where it breaks down, and how teams are making it more reliable in production. They share real examples of prompts that failed, how companies are testing for quality, and what the best teams are doing to make LLM outputs useful and predictable. 0:58 - Parahelp’s prompt example 4:59 - Different types of prompts 6:51 - Metaprompting 7:58 - Using examples 12:10 - Some tricks for longer prompts 14:18 - Findings on evals 17:25 - Every founder has become a forward-deployed engineer (FDE) 23:18 - Vertical AI agents are closing big deals with the FDE model 26:13 - The personalities of the different LLMs 27:26 - Lessons from rubrics 29:47 - Kaizen and the art of communication
@ycombinator @LightconePod Can't prompt forever, autonomy ftw 🤖
@ycombinator @LightconePod I strongly believe in prompt engineering, the way we think is going to make AI think upon our questions. The topics we emphasise are going to give us variable answers, in order to use Artificial intelligence, we gotta be intelligent first
@ycombinator @LightconePod on the topic of llm personality, i recently gave the top models the big 5 personality test. it really helped me understand when to go to which llm and why x.com/ViralManager/s…
@ycombinator @LightconePod on the topic of llm personality, i recently gave the top models the big 5 personality test. it really helped me understand when to go to which llm and why x.com/ViralManager/s…
@ycombinator @LightconePod If you're into this episode, check out @clairevo's show "How I AI", or this recent YouTube video (and new channel) for yours truly. I'm open sourcing and sharing code as much as I can as I go. youtu.be/gYeYb2EAxV0
@ycombinator @LightconePod If you're prompting a lot and need a better tool than a simple chat interface, please check out @AIFlowChat aiflowchat.com
@ycombinator @LightconePod Prompting is the new delegation.
@ycombinator @LightconePod Quickstockprompt.com let you do just that for company research. Give it a try it’s FREE.
@ycombinator @LightconePod Crazy how much hinges on getting one sentence right
Prompt engineering has clear limitations. It's not an exact science, often inefficient, and challenging to maintain consistency amid frequent frontier model updates. Even established techniques like Few-Shot prompting and Chain-of-Thought reasoning remain error-prone. For custom tasks absent from model training corpora, prompt engineering typically delivers lower accuracy than custom model training or traditional ML methods that offer greater efficiency.
@ycombinator @LightconePod Awesome insights! Prompt engineering is the future of AI 🚀
@ycombinator @LightconePod Prompt engineering will persist when you consider that everything from emails to legal documents can be thought of as prompts. LLMs need guidance - with language - to achieve a goal. Not all guidance is created equal.
@ycombinator @LightconePod 🚀 NeuralOps is building an AI-powered InfraOps copilot — automating DevOps workflows for lean teams. From infra to CI/CD, we cut weeks of setup to hours. Currently building our MVP — would love to get on @ycombinator's radar!
@ycombinator @LightconePod We moved beyond prompting into a fully patented architecture: 🔐 Real-time behavioral auth 🧠 Emotion-intent mapping 🧬 Identity-linked session flow Filed in UK & US under “Human-AI Trust Gateway” (RAVANTIS). #ZeroPassword #AITrust #LLMSecurity
@ycombinator @LightconePod People will need to get degrees in prompting. Special courses in how to prompt intelligently. Who will teach? AI? 😂
@ycombinator @LightconePod hey @ycombinator could you help me get some funds I need it for my hacker house
@ycombinator @LightconePod Prompting unlocks AI's potential to truly understand and empower users.
@ycombinator @LightconePod Prompting is now one of the most important skills to have today
@ycombinator @LightconePod if you're looking for a visual overview of all the nuggets in here, I wrote up a thread with charts you can bookmark x.com/vgshenoy/statu…
@ycombinator @LightconePod if you're looking for a visual overview of all the nuggets in here, I wrote up a thread with charts you can bookmark x.com/vgshenoy/statu…
@ycombinator @LightconePod Prompting is now an art form, not just a hack. We’re witnessing the evolution of how we collaborate with AI. Count us intrigued.
Prompting isn’t just a dev trick—it’s becoming product strategy. Loved the breakdown from @LightconePod. @Vendorapp_co , we’ve seen firsthand how better prompts = better vendor insights. LLMs are powerful, but structured inputs still rule. 🧠 vendorapp.co #AI #LLMs #PromptEngineering #MicrosoftForStartups #Vendorapp
@ycombinator @LightconePod Summary of how to improve prompting in this vid
@ycombinator @LightconePod no such thing as prefer or for or etc, cpeuxuax, say, can sayx etc an ynmw s perfx news.ycombinator.com/item?id=334792…