Mike Amundsen Focusing on Capabilities Is a Win https://buff.ly/aXdqpzY
“The first step in breaking the data-centric habit is to stop designing systems as a collection of data services, and instead design for business capabilities.” -- #IrakliNadareishvili
Administered by:
#api360
0 posts0 participants0 posts today
Been working on a small framework I’m calling GRAIL (Goal-Resolution through Affordance-Informed Logic). It’s not a planner, not a workflow engine, and success does not depend on an AI/MCP environment.
Today I am sharing this blog post from #RyanDay: "Join me for an API Superstream" https://buff.ly/DMKAXlt
Ryan will be one of the featured speakers at the upcoming #OReillyMedia API//AI superstream .
Check out Ryan's post for details and how to register.
Signals from Our Futures Past | Mike Amundsen | Substack https://mamund.substack.com/
Join me for O’Reilly Media’s “APIs and Agents” Superstream event Wednesday, July 17, 2025.
register here: https://www.oreilly.com/live-events/api-superstream-apis-and-agents/0642572173432/0642572173425/
15 years ago, Steve Wozniak proposed The Coffee Test as a benchmark for machine intelligence: walk into a stranger’s house and make coffee.
Today, that challenge is surprisingly relevant as AI agents begin to coordinate, adapt, and collaborate — not just call APIs.
In this new long-form piece, I explore how protocols like MCP, affordances, and decades-old ideas from Engelbart and Nelson are finally converging.
Read it here: https://buff.ly/3vc9f6y
Meta Says It's Okay to Feed Copyrighted Books Into Its AI Model Because They Have No "Economic Value" https://bit.ly/4jL5IlN
ALPS and MCP: Interaction with AI created by REST constraints https://buff.ly/VQuHjIO
" The principles of REST, designed in 2000, and ALPS, which defines its semantics, have universal values that can respond surprisingly naturally to the challenge of interacting with LLMs" -- #koriym
What's wrong with AI-generated docs https://buff.ly/xAp81oX
let me tell you what’s wrong with docs and docs sets entirely generated by LLMs.
passo.uno · What's wrong with AI-generated docsIn what is tantamount to a vulgar display of power, social media has been flooded with AI-generated images that mimic the style of Hayao Miyazaki’s anime. Something similar happens daily with tech writing, folks happily throwing context at LLMs and thinking they can vibe write outstanding docs out of them, perhaps even surpassing human writers. Well, it’s time to draw a line. Don’t let AI influencers studioghiblify your work as if it were a matter of processing text.
Transforming the Software Development Lifecycle (SDLC) with Generative AI | Amazon Web Services
"Considering code generation, or application development more broadly, generative AI is not only changing the way applications are built, but the way they are envisioned, designed, tested, documented, and deployed."
ChatGPT's odds of getting code questions correct are worse than a coin flip
https://www.theregister.com/2023/08/07/chatgpt_stack_overflow_ai/
"'Our analysis shows that 52 percent of ChatGPT answers are incorrect and 77 percent are verbose,' the team's paper concluded. 'Nonetheless, ChatGPT answers are still preferred 39.34 percent of the time due to their comprehensiveness and well-articulated language style.' Among the set of preferred ChatGPT answers, 77 percent were wrong." -- #ThomasClaburn
The Register · ChatGPT's odds of getting code questions correct are worse than a coin flip