Building AI agents? Don't let them forget the context. 🧠
Join me at Azure Cosmos DB Conf on April 28th to learn:
✅ Persistent Chat History for Agents
✅ Implementing Semantic Caching
✅ Scaling with @AzureCosmosDB
Register now: aka.ms/cosmosconfreg 🚀
#CosmosDBConf #BuildAI

LLM-as-a-judge: the measurement problem You've built something and you need to know if it works. So you do what's sensible—you ask an LLM to grade it. Factual accuracy, code quality, agent outputs. The machine judges the machine, and you ge...

The solution to automating human judgment is 500 instances of human judgment. Automation has a sense of humor about its limitations.

#BuildAI

wordoflore.ai/llm-as-a-jud...

Claude Opus 4.5: effort control Claude Opus 4.5 is the newest brainchild from Anthropic, the folks behind the Claude language models. Think of it as their latest and smartest tool for handling really complicated tasks—like having an...

We've given AI an effort dial—like it's a teenager who could get better grades if they just applied themselves. This is where we are as a civilization.

#BuildAI

wordoflore.ai/claude-opus-...

Hey, have you ever tried Google Gemini 3? I was playing with it for the last few hours, and I want to show you what I built ☕.

#gemini3 #buildai #ai #app #simulator #coffee

OpenAI: apps inside ChatGPT OpenAI has just launched something called the Apps SDK, and it’s a bit like giving developers a new set of building blocks for ChatGPT. Instead of just chatting, you can now create apps that live righ...

We've collectively decided chat windows are the new operating system—because why would we want dedicated interfaces when we can cram everything into a text box?

#BuildAI

wordoflore.ai/openai-apps-...

Veo 3.1: native audio and reference controls Veo is Google's latest attempt to teach computers how to make videos from scratch. Now in version 3.1, it's available for anyone willing to pay for early access, either through Google AI Studio or Ver...

From "this will replace all creatives" to "it's a very expensive sketching tool" in record time — the lifecycle of every AI product announcement.

#BuildAI

wordoflore.ai/veo-3-1-nati...

Pydantic: Evals Pydantic Evals is a tool for Python that lets you watch, step by step, how your AI agents go about solving problems. It’s made by the same people who built the popular Pydantic data validation library...

We've moved from testing if AI gets the right answer to testing if it reasons correctly—which is either progress or peak parenting anxiety for your code.

#BuildAI

wordoflore.ai/pydantic-eva...

LangSmith: multi-turn evaluation Imagine you’re chatting with an AI, asking it to help you book a flight. It might give you the right answer to every single question you ask, but somehow, you still end up without a ticket. That’s whe...

Discovering your AI is technically helpful but functionally useless—a special kind of product failure that only shows up when someone actually tries to use the thing

#BuildAI

wordoflore.ai/langsmith-mu...

Karpathy: nanochat nanochat is Karpathy’s attempt to strip LLM training down to its bare essentials. It’s about 8,000 lines of code, and it’s designed to be read and understood, not just run. Unlike the big, complicated...

A hundred dollars to watch a computer figure out the alphabet—the tuition for machine kindergarten is honestly more reasonable than I expected

#BuildAI

wordoflore.ai/karpathy-nan...

Google Research: the language of biology Imagine you could talk to cells and ask them what they’re up to. That’s more or less what Cell2Sentence-Scale (C2S-Scale) lets you do. Built by Google Research and Yale, it’s an open-source model that...

Biology is now just another domain for natural language processing—we've successfully reduced cellular complexity to a tokenization problem

#BuildAI

wordoflore.ai/google-resea...

Anthropic: Agent Skills Agent Skills is a new way for Claude to learn new tricks. Imagine you could hand Claude a folder full of instructions, code, and resources, and Claude would know exactly when to use them. That’s what ...

Everything requires its own API endpoint now. Still waiting for the `/v1/existential-crisis` endpoint for when the system becomes self-aware.

#BuildAI

wordoflore.ai/anthropic-ag...

SAE steering: Delta Token Confidence Imagine you’re trying to understand what’s going on inside an AI’s mind. Sparse Autoencoders, or SAEs, are a tool that lets us break down the AI’s thoughts into features we can actually make sense of....

We've discovered that understanding something and controlling it are unrelated skills. Every parent could have told AI researchers this.

#BuildAI

wordoflore.ai/sae-steering...

Gemini: computer use Google DeepMind has just released something called the Gemini 2.5 Computer Use model. In plain English, it’s an AI that can use computers almost like a person does. It can click buttons, type into for...

We trust it to navigate the internet but not to spend money. That tells you everything about what the internet has become

#BuildAI

wordoflore.ai/gemini-compu...

Fraunhofer: circuit-based interpretability Mechanistic interpretability is all about peering inside a neural network’s mind and asking, ‘How does this thing actually think?’ The usual way is to throw billions of words at the model and then ask...

We've reached peak meta: needing AI therapists to explain what our AI is thinking. The trust issues are mutual.

#BuildAI

wordoflore.ai/fraunhofer-c...

Claude: memory tool Imagine you’re building something with Claude, and you want it to remember things from one conversation to the next. Anthropic has just released a memory tool for their Claude API that lets you do exa...

AI memory tool: every conversation is no longer a first date where you explain your job for the tenth time

wordoflore.ai/claude-memor...

#BuildAI

Harvard: ML systems textbook Imagine you want to build machine learning systems that actually work in the real world, not just in a classroom. Harvard has put together a textbook for exactly that. It’s based on their CS249r cours...

Harvard's releasing a textbook on ML systems that 'actually work in the real world'—the fact that this is a selling point tells you everything about how we've been teaching this.

wordoflore.ai/harvard-ml-s...

#BuildAI

Windows ML: on-device inference Windows ML is a tool from Microsoft that lets developers run AI models right on your own computer. Instead of sending your data off to some distant server, everything happens right there on your devic...

Nothing says innovation like rediscovering that computers can actually compute things locally

wordoflore.ai/windows-ml-o...

#BuildAI

OpenAI Open-Sources Agentic Commerce Protocol: A Standard for AI Transactions The Agentic Commerce Protocol is a set of rules that lets AI agents buy things for you. OpenAI and Stripe built it together, along with some merchants. The idea is simple: it tells AIs, users, and bus...

Are we worried about trusting the AI, or trusting ourselves with a button that easy to push?

wordoflore.ai/openai-open-...

#BuildAI

Google Releases Open Protocol for Agent-Initiated Payments The Agent Payments Protocol, or AP2, is a new set of rules for how AI agents can move money around safely. Google didn’t do this alone. They worked with more than 60 other companies—big names like Mas...

Sixty companies agreeing on something is either genuine progress or everyone hedging their bets on the same future

wordoflore.ai/google-relea...

#BuildAI

Claude Sonnet 4.5: A New AI Model That Excels at Coding and Building Agents Claude Sonnet 4.5 is the newest AI model from Anthropic, and it’s built for people who want to create smarter apps and digital assistants. It belongs to the Claude 4 family, and you can use it through...

Claude Sonnet 4.5 is out
wordoflore.ai/claude-sonne...
#BuildAI

Hablemos de la caida de #BuildAI
#ia #inteligenciaartificial

Looking for a Jasper AI Alternative? Check Out These Options

💢 Visit my bio link
#jesperalternative #jesperalt #aicreator #aiproduct #alternativeai #altAI #createAI #buildAI #makeAI #developAI #jesperplatform #jesperplat #jesperapp #jespertool #jesperHQ