Discussion

• @dposorio @dposorio on bluesky

  I was pissed AI didn't do the dishes when I asked, but ends up I didn't ask it the right way.  [embedded post]

• @andrewnebus Andrew Nebus on bluesky

  “Context engineering” is an interesting change as I rarely see “prompt engineering” anymore  —  But even people do better when you don't drop them into a conversation mid-sentence 🤖🧠 [embedded post]

• @rjcc Richard Lawler on bluesky

  It'd be easier to believe that ai bots are easy to use and more efficient if the people who use them the most didn't keep making up new kinds of experts in how to make them work.  [embedded post]

• @karpathy Andrej Karpathy on x

  +1 for “context engineering” over “prompt engineering”. People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window

• @tobi Tobi Lutke on x

  I really like the term “context engineering” over prompt engineering. It describes the core skill better: the art of providing all the context for the task to be plausibly solvable by the LLM.

• @amasad Amjad Masad on x

  @tobi Yes!

• @richardblythman Richard Blythman on x

  1/ @karpathy nailed it: more context → better answers. But what if your context is locked behind OAuth scopes, consent screens, and brittle integrations? At @NapthaAI, this was our biggest pain point building agents. So we built a better way. We call it OneDollarOAuth. 🧵

• @simonw Simon Willison on x

  I haven't spotted this, but it's exactly correct: “context engineering” captures the fact that the previous responses from the model are a key part of the process, “prompt engineering” suggests that it's only the user prompts that matter

• @mckaywrigley Mckay Wrigley on x

  @tobi Totally agree. These days you get wayyy less perf bonus out of dumb tricks like “I'll pay you $100 if you get this right”, which is how it should be. All of the alpha is in assembling context well to reduce the fog of war for the model. It's converging to human-ish info nee…

• @simonw Simon Willison on x

  I think context engineering is going to stick - unlike “prompt engineering” it has an inferred definition that's much closer to the intended meaning, which is to carefully and skillfully construct the right context to get great results from LLMs

• @swaseyonswdev @swaseyonswdev on x

  @simonw I think it's going to stick because it actually jibes with the underlying “autocomplete” reality, which is what the initial output of the model is *part of the context* for the rest of the output.

• @simonw Simon Willison on x

  “Prompt engineering” suffers from a thing where many people's inferred definition is that it's a laughably pretentious term for typing things into a chatbot! https://simonwillison.net/...