The House of Representatives recently advanced a major new “market structure” bill with overwhelming bipartisan support (294 to 134, with 78 Democrats supporting). This bill, the Digital Asset Market Clarity Act or “CLARITY Act” (HR 3633) would establish a clear regulatory framework for digital asset markets. The bill now progresses to the Senate, which is working on its own version of market structure legislation that will be informed by CLARITY. If passed, this bill will establish clear rules of the road for blockchain systems — ending the years of uncertainty that have stifled innovation, exposed consumers to harm, and favored profiteers embracing opacity over the entrepreneurs pursuing transparency. Like the Securities Act of 1933, which established investor protections and powered a century of U.S. capital formation, the CLARITY Act could be a generational law. When our legal frameworks are designed to both foster innovation and protect consumers, America leads — and the world benefits. CLARITY is that kind of opportunity. While this legislation builds on the bipartisan momentum of last year’s FIT21 bill, CLARITY improves upon it in several key ways, which we outline below: covering what the builders need to know, and why this bill is crucial to aligning innovation, consumer protection, and U.S. national security. Learn more about The CLARITY Act in the thread below. And find the full post by @milesjennings & Aiden Slavin:

+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.