Explore
37,123 skills indexed with the new KISS metadata standard.
DALL·E-3 is the latest version of our DALL-E text-to-image generation models. As the current state of the art in text-to-image generation, DALL·E is capable of generating high-quality images across a wide variety of domains. If you're interested in more technical details of how DALL·E-3 was built, y
The [OpenAI API embeddings endpoint](https://beta.openai.com/docs/guides/embeddings) can be used to measure relatedness or similarity between pieces of text.
When GPT-3 fails on a task, what should you do?
People are writing great tools and papers for improving outputs from GPT. Here are some cool ones we've seen:
The [`gpt-oss` models](https://openai.com/open-models) were trained on the harmony response format for defining conversation structures, generating reasoning output and structuring function calls. If you are not using `gpt-oss` directly but through an API or a provider like Ollama, you will not have
[Large language models][Large language models Blog Post] are functions that map text to text. Given an input string of text, a large language model predicts the text that should come next.
ROOST and OpenAI have prepared a guide that explains how to write policy prompts that maximize [gpt-oss-safeguard's](https://github.com/openai/gpt-oss-safeguard) reasoning power, choose the right policy length for deep analysis, and integrate oss-safeguard's reasoning outputs into production Trust &
Codex and the `gpt-5.2-codex` model (recommended) can be used to implement complex tasks that take significant time to research, design, and implement. The approach described here is one way to prompt the model to implement these tasks and to steer it towards successful completion of a project.
This course is intended to provide you with a comprehensive step-by-step understanding of how to engineer optimal prompts within Claude.
generic skill
- origins of attention https://x.com/karpathy/status/1864023344435380613
Explanation and techniques used described on the blog: https://lspace.swyx.io/p/reverse-prompt-eng
2. ai scientist - self improvement/automate AI research
> this ended up being the best list — [Andrew Chen](https://twitter.com/andrewchen/status/1642626083962130432?s=46&t=90xQ8sGy63D2OtiaoGJuww)
- https://www.youtube.com/watch?v=Ums_VKKf_s4
- gdb's [developer demo livestream](https://www.youtube.com/watch?v=outcGtbnMuQ)
- https://platform.openai.com/docs/guides/fine-tuning
https://willthompson.name/what-we-know-about-llms-primer#block-920907dc37394adcac5bf4e7318adc10
Podcast prep notes: https://docs.google.com/document/d/1VK5Zs7rYggF0qiceghlR2xtlGgk-g4pkEgJqnsG_sys/edit?usp=sharing
- replaces model selector?
- March 23 - plugins preview https://openai.com/blog/chatgpt-plugins
easiest way i know to run the benchmarks yourself is https://github.com/EleutherAI/lm-evaluation-harness
> ⚠️ This is a **very** new/immature list, created for [the Latent Space Demo Day](https://lspace.swyx.io/p/demo-day-2023). The category labels not that well thought through. Please [get in touch](https://discord.gg/gR6yP6wbfq) if you have better ideas for how to organize this, it is welcome.
- Generative Tech FAST Pre-Seed and Seed Funding in 9 Days