Let's hustle @interaction let's get this https://t.co/UFN6Yhs0wa £1 down to £0 through the back door😎🚪
I feel like I'm playing Monkey Island trying to defeat LeChuck - one level to go...
+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 with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits.
On top of context engineering itself, an LLM app has to:
- break up problems just right into control flows
- pack the context windows just right
- dispatch calls to LLMs of the right kind and capability
- handle generation-verification UIUX flows
- a lot more - guardrails, security, evals, parallelism, prefetching, ...
So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.
Here's how Gemini 2.5 Flash-Lite writes the code for a UI and its contents based solely on the context of what appears in the previous screen - all in the time it takes to click a button. 💻 ↓
Hoyte van Hoytema (HER, NOPE, Ad Astra, Oppenheimer) shot a Volvo short film recently.
there's some insane lens being used throughout - it looks wild. full short in the reply.
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.
https://t.co/YYpOAcrXQ3
Prompt: “Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes.”
A few months ago, a client asked that I give a presentation to her team about how to give better creative feedback. These tips work just as well for aspiring creative directors, so here it is as a🧵 /1
Today we are launching Rewind: the search engine for your life https://t.co/05G3jkDnco
It’s a macOS app that enables you to find anything you’ve seen, said, or heard.
We’re also announcing that we’ve raised $10m at a $75m valuation led by Andreessen Horowitz.
(1/23)
'Ad workers of today are more likely to churn out brief video clips for sites such as YouTube — whose viewers regard them as a nuisance — or targeted emails that aim to generate immediate sales, than to dream up brand-building commercials'
via @davetrott
https://t.co/ky77iUH8FD
Network news: Unplug, tell stories & have big ideas featuring @london_kindred, @MrBenStevenson, @annafern45 & https://t.co/3NkUi6dRHD
https://t.co/36GfiXaMLW