# ai evaluation — RSS Amplifier Recent posts from the 3 feeds in the RSS Amplifier directory that cover ai evaluation. Page: Feed: --- ## [Connecting to Any OpenAI-Compatible Endpoint with \`Microsoft.Extensions.AI.OpenAI\`](https://codetraveler.io/2026/08/17/connecting-to-any-openai-compatible-endpoint-with-microsoft-extensions-ai-openai/) _2026-08-17 · Brandon Minnick · Code Traveler_ Did you know the Microsoft.Extensions.AI.OpenAI NuGet Package works with far more than just OpenAI? One adapter package unlocks every OpenAI-compatible endpoint on the internet — and even the ones on your laptop! This is Part 6 of our Microsoft.Extensions.AI series. We've already ## [Evaluating AI Safety in .NET with \`Microsoft.Extensions.AI.Evaluation.Safety\`](https://codetraveler.io/2026/08/10/evaluating-ai-safety-in-net-with-microsoft-extensions-ai-evaluation-safety/) _2026-08-10 · Brandon Minnick · Code Traveler_ Last week we tested whether our LLM's answers were accurate . But are they safe for our company to use, responsing with no harmful content or violence? Microsoft.Extensions.AI.Evaluation.Safety makes it easy to check. This is Part 5 of our Microsoft.Extensions.AI series. In Part ## [Five Reasons AI Regulation Is Coming To The US, How And When](https://carvao.substack.com/p/five-reasons-ai-regulation-is-coming) _2026-08-07 · Paulo Carvao · Tech and Democracy_ AI Regulation shifts from debate to enforcement as cyber incidents and U.S. politics push frontier labs toward trust-building oversight amid rising 2026 pressure. ## [Unit Testing LLMs: Evaluating LLM Quality in .NET with \`Microsoft.Extensions.AI.Evaluation\`](https://codetraveler.io/2026/08/03/unit-testing-llms-evaluating-llm-quality-in-net-with-microsoft-extensions-ai-evaluation/) _2026-08-03 · Brandon Minnick · Code Traveler_ How do we unit test an LLM that never gives the same answer twice? Microsoft.Extensions.AI.Evaluation makes it easy. This is Part 4 of our Microsoft.Extensions.AI series. In Part 1 we built a chat app with IChatClient — but how do we know its answers are ## [2026 July "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-july-ai-evaluation-digest) _2026-07-31 · AI Evaluation · The AI Evaluation Substack_ The Lab Leaks We Can Actually Prove ## [Generating Images in .NET with \`IImageGenerator\`](https://codetraveler.io/2026/07/27/generating-images-in-net-with-iimagegenerator/) _2026-07-27 · Brandon Minnick · Code Traveler_ Did you know Microsoft.Extensions.AI can generate images too? IImageGenerator makes it easy! This is Part 3 of our Microsoft.Extensions.AI series. In Part 1 we created an AI Chat Bot with an LLM using IChatClient , and in Part 2 we built semantic search using IEmbeddingGenerator . This week, ## [Adding Semantic Search to .NET Apps with \`IEmbeddingGenerator\`](https://codetraveler.io/2026/07/20/adding-semantic-search-to-net-apps-with-iembeddinggenerator/) _2026-07-20 · Brandon Minnick · Code Traveler_ Have you ever typed "How do I get my money back?" into a search box and gotten zero results, because the docs only ever say "refund policy"? Embeddings fix this! And Microsoft.Extensions.AI makes it easy than ever to do. This is Part 2 of ## [Creating an AI Chat Bot in .NET with \`IChatClient\`](https://codetraveler.io/2026/07/16/adding-ai-to-your-net-app-with-ichatclient/) _2026-07-16 · Brandon Minnick · Code Traveler_ Are you looking to implement AI in your .NET app? Microsoft.Extensions.AI makes it easy! This is the first post in a new series where we'll learn Microsoft.Extensions.AI together, one building block at a time. Let's start with the most important building block ## [You Outsourced the AI—but You Still Own the Risk](https://carvao.substack.com/p/you-outsourced-the-aibut-you-still) _2026-07-09 · Paulo Carvao · Tech and Democracy_ Enterprises increasingly deploy AI systems they did not build, yet courts and regulators are holding them responsible. ## [Connect Education To Jobs And Create An AI Workforce Transition Plan](https://carvao.substack.com/p/connect-education-to-jobs-and-create) _2026-07-08 · Paulo Carvao · Tech and Democracy_ An AI workforce transition needs more than retraining. P-TECH shows how education, employers and credentials can connect workers to jobs reshaped by AI. ## [Non-custodial Crypto Payments & Escrow (Sponsored)](https://crawlproof.com/a/uQ3mdlLz0zAl) _2026-07-08 · **Sponsored**_ Accept multi-chain crypto with trustless escrow, instant confirmations, and no KYC ## [How Anthropic, OpenAI, The Vatican And Congress Want To Govern AI](https://carvao.substack.com/p/how-anthropic-openai-the-vatican) _2026-07-07 · Paulo Carvao · Tech and Democracy_ Anthropic, OpenAI, the Vatican and Congress all agree AI needs guardrails—but they disagree on what should be protected first, from catastrophic risk to human dignity and U.S. competitiveness. ## [2026 June "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-june-ai-evaluation-digest) _2026-06-26 · AI Evaluation · The AI Evaluation Substack_ Multiply and die ## [Making Sense Of The AI IPO Tsunami Heading For Wall Street](https://carvao.substack.com/p/making-sense-of-the-ai-ipo-tsunami) _2026-06-12 · Paulo Carvao · Tech and Democracy_ The AI IPO wave will test whether OpenAI, Anthropic and SpaceX can turn private-market valuations into public-market trust and durable investor demand. ## [Trump's AI Evaluations Order: Right Policy, Unfinished Governance](https://carvao.substack.com/p/trumps-ai-evaluations-order-right) _2026-06-10 · Paulo Carvao · Tech and Democracy_ Trump’s AI evaluation order advances national security testing but raises concerns over secrecy, industry access and public accountability. ## [2026 May "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-may-ai-evaluation-digest) _2026-05-29 · AI Evaluation · The AI Evaluation Substack_ 2001… subscribers odyssey ## [OpenAI And Anthropic Are Testing Two Very Different AI Business Models](https://carvao.substack.com/p/why-ai-profitability-belongs-to-enterprise) _2026-05-27 · Paulo Carvao · Tech and Democracy_ AI profitability favors enterprise over consumer scale. Anthropic reaches profit as OpenAI plans IPO. Which model wins with public market investors and why it matters. ## [Build Modern Tech Policy By Hiring The Students Who Already Understand It](https://carvao.substack.com/p/build-modern-tech-policy-by-hiring) _2026-05-21 · Paulo Carvao · Tech and Democracy_ Hire the next generation of modern tech policy talent now. Students already understand AI, law, governance and the skills institutions urgently need. ## [AI, Democracy And The Politics Of The Kitchen Table](https://carvao.substack.com/p/ai-democracy-and-the-politics-of) _2026-05-15 · Paulo Carvao · Tech and Democracy_ AI is becoming a kitchen table issue as data centers, electricity bills, jobs, privacy, children and democracy collide before the 2026 midterms. ## [Pre-Deployment AI Evaluation Moves From China’s Model To Washington](https://carvao.substack.com/p/pre-deployment-ai-evaluation-moves) _2026-05-14 · Paulo Carvao · Tech and Democracy_ Washington’s new pre-deployment AI evaluation push echoes China’s model and exposes why Congress needs stable, bipartisan AI policy. ## [When Federal Agencies Pick AI Vendors, They Are Buying Different Policy Interpretations](https://carvao.substack.com/p/when-federal-agencies-pick-ai-vendors) _2026-05-13 · Paulo Carvao · Tech and Democracy_ Harvard Kennedy School research shows how AI can analyze AI policy and why different models may interpret the same policy in different ways. ## [Persona-led AI publishing (Sponsored)](https://crawlproof.com/a/qasVdDRuQISn) _2026-05-13 · **Sponsored**_ Generate drafts, schedule subdomain publishing, and keep human review where needed. ## [2026 April "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-april-ai-evaluation-digest) _2026-04-24 · AI Evaluation · The AI Evaluation Substack_ Nerf, Noise, or Narrative? ## [Five Reasons Anthropic Kept Its Cybersecurity Breakthrough Invite-Only](https://carvao.substack.com/p/five-reasons-anthropic-kept-its-cybersecurity) _2026-04-15 · Paulo Carvao · Tech and Democracy_ Anthropic’s invite-only rollout of Project Glasswing shows how frontier AI is becoming a premium enterprise product, shaped by scarcity, safety and market strategy. ## [National Policy Framework Turns AI Preemption Into A 2026 Political Test](https://carvao.substack.com/p/national-policy-framework-turns-ai) _2026-04-09 · Paulo Carvao · Tech and Democracy_ Trump’s AI framework pushes federal preemption to the center of U.S. AI policy, setting up a 2026 fight over state power, accountability and national standards. ## [2026 March "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-march-ai-evaluation-digest) _2026-03-27 · AI Evaluation · The AI Evaluation Substack_ Physics Envy ## [AI Leadership Faces Its Defining Test As Anthropic Takes The Pentagon To Court](https://carvao.substack.com/p/ai-leadership-faces-its-defining) _2026-03-18 · Paulo Carvao · Tech and Democracy_ Anthropic sues the Pentagon while OpenAI signs a deal. What two CEOs' contrasting choices reveal about AI leadership, market value, and ethical risk. ## [The Conscience Clause](https://carvao.substack.com/p/the-conscience-clause) _2026-03-11 · Paulo Carvao · Tech and Democracy_ The Anthropic-Pentagon standoff exposed a dangerous vacuum: AI is reshaping national security, but no law governs how. Who decides, and who should? ## [Mass-surveillance is a reality in the U.S.](https://carvao.substack.com/p/mass-surveillance-is-a-reality-in) _2026-02-28 · Paulo Carvao · Tech and Democracy_ What five different Chatbots, three American and two Chinese, tell us? ## [2026 February "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-february-ai-evaluation-digest) _2026-02-27 · AI Evaluation · The AI Evaluation Substack_ Quis custodiet ipsos custodes? ## [Should AI Go To War? Anthropic And The Pentagon Fight It Out](https://carvao.substack.com/p/should-ai-go-to-war-anthropic-and) _2026-02-27 · Paulo Carvao · Tech and Democracy_ Explore the clash between Anthropic and the Pentagon over military AI. Learn how debates on ethical guardrails and autonomous weapons shape the future of global warfare. ## [The Problem With Tech's Latest “Something Big Is Happening” Manifesto](https://carvao.substack.com/p/the-problem-with-techs-latest-something) _2026-02-20 · Paulo Carvao · Tech and Democracy_ A critical take on Matt Shumer’s viral AI manifesto, examining labor market disruption, hype cycles and the real path to responsible AI adoption. ## [Watch chovy live code (Sponsored)](https://crawlproof.com/a/0n8su1E7fXoS) _2026-02-20 · **Sponsored**_ Join Mosh Coding streams with collaborative screen sharing and remote control, open source. ## [2026 January "AI Evaluation" Digest](https://aievaluation.substack.com/p/2026-january-ai-evaluation-digest) _2026-01-30 · AI Evaluation · The AI Evaluation Substack_ A monthly digest of the latest developments, research trends and key initiatives in the realm of AI evaluation. ## [Should The U.S. Risk Its AI Edge By Letting Nvidia Sell Chips To China?](https://carvao.substack.com/p/should-the-us-risk-its-ai-edge-by) _2026-01-29 · Paulo Carvao · Tech and Democracy_ A clear-eyed look at export controls, national security, innovation and America’s long-term AI leadership. ## [Introducing Bindable Property Source Generators](https://codetraveler.io/2026/01/29/introducing-bindable-property-source-generators/) _2026-01-29 · Brandon Minnick · Code Traveler_ I am excited to announce two new source generators introduced in CommunityToolkit.Maui v14.0.0 : \[BindableProperty\] \[AttachedBindableProperty\\] These new source generators make it easier than ever to create a BindableProperty in your .NET MAUI apps. In fact, all Bindable Properties in CommunityToolkit.Maui are now automatically ## [AI In 2026: The Year AI Meets Enterprise And Politics](https://carvao.substack.com/p/ai-in-2026-the-year-ai-meets-enterprise) _2026-01-12 · Paulo Carvao · Tech and Democracy_ AI in 2026 faces limits to scaling, new innovation beyond large models, rising enterprise adoption and mounting pressure on Congress to regulate. ## [2025 December "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-december-ai-evaluation-digest) _2025-12-26 · AI Evaluation · The AI Evaluation Substack_ Call for Tributes: Your test of time. ## [2025 November "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-november-ai-evaluation-digest) _2025-11-28 · AI Evaluation · The AI Evaluation Substack_ Hitting a wall? Seeing is all you need ## [2025 October "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-october-ai-evaluation-digest) _2025-10-31 · AI Evaluation · The AI Evaluation Substack_ "Beware; for I am fearless, and therefore powerful.” ## [Is the Definition of AGI a Percentage?](https://aievaluation.substack.com/p/is-the-definition-of-agi-a-percentage) _2025-10-31 · Lorenzo Pacchiardi · The AI Evaluation Substack_ Zachary Tidler, Marko Tešić, Lorenzo Pacchiardi, John Burden, Lexin Zhou, Manuel Cebrián, Fernando Martínez-Plumed, Jose Hernandez-Orallo ## [2025 September "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-september-ai-evaluation-digest) _2025-09-26 · AI Evaluation · The AI Evaluation Substack_ What could possibly go wrong? ## [2025 August "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-august-ai-evaluation-digest) _2025-08-29 · AI Evaluation · The AI Evaluation Substack_ Between a rock and a hard place ## [2025 July "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-july-ai-evaluation-digest) _2025-07-25 · AI Evaluation · The AI Evaluation Substack_ Long live OpenML! ## [2025 June "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-june-ai-evaluation-digest) _2025-06-27 · AI Evaluation · The AI Evaluation Substack_ Illusion is all you need ## [2025 May "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-may-ai-evaluation-digest) _2025-05-30 · AI Evaluation · The AI Evaluation Substack_ Ethical standards in AI evaluation ## [2025 April "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-april-ai-evaluation-digest) _2025-04-25 · AI Evaluation · The AI Evaluation Substack_ En attendant Turing: a Tragicomedy in Two Acts ## [2025 March "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-march-ai-evaluation-digest) _2025-03-28 · AI Evaluation · The AI Evaluation Substack_ Overhauling Difficulty in Item Response Theory. ## [Introducing AWSSDK.Extensions.Bedrock.MEAI](https://codetraveler.io/2025/03/25/introducing-awssdk-extensions-bedrock-meai-2/) _2025-03-25 · Brandon Minnick · Code Traveler_ Are you looking to add GenAI functionality to your .NET app? AWSSDK.Extensions.Bedrock.MEAI makes it easy. Let's define what some of these words mean, then check out how to use this NuGet Package in our apps! You're also welcome to skip the definitions and ## [2025 February "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-february-ai-evaluation-digest) _2025-02-28 · AI Evaluation · The AI Evaluation Substack_ It’s high time to change the paradigm. ## [2025 January "AI Evaluation" Digest](https://aievaluation.substack.com/p/2025-january-ai-evaluation-digest) _2025-01-31 · AI Evaluation · The AI Evaluation Substack_ Distil, baby, distil!