Intel
Page 48
Andrew Ng@AndrewYNg
Multi-agent systems break when every team's framework choice needs its own integration. ACP puts agents behind a unified REST interface hosted in an ACP server, with a defined agent lifecycle — and a comparison against MCP and A2A that clarifies which layer each occupies.
Why it mattersACP standardizes agent-to-agent calls behind one REST interface so teams can swap frameworks or agent versions without refactoring the whole system — and it clarifies where MCP and A2A each fit.
articleEugene Yan
Evaluating Long-Context Question & Answer Systems
Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.
Why it mattersHow to evaluate long-context Q&A systems: datasets, methodology and the benchmark pitfalls that make scores lie.
Phoenix.new – The Remote AI Runtime for Phoenix
Chris McCord launches Phoenix.new, a browser-based coding agent tailored to Elixir and Phoenix.
Why it mattersA coding agent purpose-built for Elixir and Phoenix, running with root in a disposable VM so the agent can install and execute freely — a direct answer to LLM agents being weakest outside Python and JavaScript.
articlefly.io
Introducing Roast
Shopify open-sourced Roast, a convention-oriented framework for AI workflows defined in YAML and markdown that interleaves agent steps with regular code.
Why it mattersAn open-source orchestration framework for the pattern most agent work actually needs: decomposed steps where AI calls and deterministic code interleave, configured declaratively rather than hidden in a mega-prompt.
articleShopify Engineering
Understanding and Coding the KV Cache in LLMs from Scratch
A hands-on technical tutorial that explains how key-value (KV) caches speed up LLM inference, walking through a from-scratch, human-readable PyTorch implementation.
Why it mattersIf you want to actually understand how KV caching accelerates LLM inference rather than just calling an API, this walks through a human-readable from-scratch PyTorch implementation and demonstrates a concrete ~5x speedup on a 124M model.
articleSebastian Raschka, PhD
How We Built Our Multi-Agent Research System
An Anthropic engineering post covering the challenges and lessons learned in building Claude's multi-agent Research system.
Why it mattersIt lays out a concrete orchestrator-worker pattern for parallel research agents — how to split subtasks, write effective sub-agent prompts, handle token/context budgets, and evaluate non-deterministic multi-agent output.
articleAnthropic
Andrew Ng@AndrewYNg
A working definition of the GenAI Application Engineer: fluency across many AI building blocks rather than one, combined with the ability to build systems dramatically faster using AI assistance. Includes the interview questions used to tell the two capabilities apart.
Why it mattersNames the specific breadth — evals, guardrails, RAG, voice stack, embeddings, MCP, agentic browser use — that separates someone who can call an LLM API from someone who can compose systems, plus how to interview for it.
What are MCP Servers?
An attempt to make Model Context Protocol concrete beyond the official analogy, working through what an MCP server actually exposes to an LLM and why the Alexa-skill and 'API 2.0' framings explain the discovery model better.
Why it mattersGives usable mental models for MCP — tool skills an LLM installs and discovers, rather than an API you call — which clarifies when writing a server is worth it and what the protocol actually exchanges.
articlefly.io
Magistral
Mistral's first reasoning model arrives in two variants.
Why it mattersAn openly released 24B reasoning model with inspectable reasoning traces that stay in the prompt's language gives you a self-hostable option for cases where you need to verify the path, not just the answer.
articlemistral.ai
articleQwen Team
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
The Qwen3 Embedding series targets text embedding, retrieval and reranking, built on the Qwen3 foundation models and leaning on their multilingual understanding for state-of-the-art results across benchmarks.
Why it mattersOpen-weight (Apache 2.0) multilingual embedding and reranking models built on Qwen3 give you a self-hostable alternative to proprietary embedding APIs for RAG and retrieval pipelines.
Andrew Ng@AndrewYNg
Databricks and a DSPy co-lead teach signature-based programming, MLflow tracing to see how each pipeline stage performs, and the optimizer that tunes prompts — few-shot examples included — against evals, then re-tunes the system when you swap in a newer model.
Why it mattersModel swaps silently degrade prompts tuned for the old one; DSPy re-optimizes the whole pipeline from a handful of eval examples instead of manual rewriting.
Introducing Mistral Code
A coding assistant assembled from open foundations.
Why it mattersMistral Code bundles models, an in-IDE assistant, and enterprise controls on top of the open-source Continue project, deployable in cloud, on reserved capacity, or on air-gapped on-prem GPUs.
articlemistral.ai
My AI Skeptic Friends Are All Nuts
A veteran systems programmer takes apart the standard objections to LLM-assisted coding, insisting that agent setups which actually run and iterate on generated code are a different thing from the autocomplete critics tried two years ago.
Why it mattersConfronts the common objections to LLM coding — hallucination, code quality, craft — with the practical counterpoint that agent loops which compile and run the code change the calculus for serious developers.
articlefly.io
Codestral Embed
Mistral's first embedding model built for code, benchmarked on SWE-Bench-style issue retrieval and text-to-code lookup against Voyage Code 3, Cohere Embed v4 and OpenAI's large embedder.
Why it mattersRetrieval quality bounds coding-agent quality; this model claims to beat leading code embedders even truncated to 256 dimensions at int8, which materially cuts vector storage cost for repo-scale indexes.
articlemistral.ai
LLM Evals: Everything You Need to Know
Curated answers to the questions that came up most while teaching AI evals to 700-plus engineers and product managers, offered as sharp working opinions rather than universal rules.
Why it mattersA dense, opinionated field guide to LLM evals covering error analysis, LLM-as-judge design, and critique shadowing — the practical workflows for actually improving AI products, not just theory.
articleHamel Husain
Andrew Ng@AndrewYNg
Agentic Document Extraction cut median processing time from 135 seconds to 8 while still pulling diagrams, charts and form fields out of PDFs as LLM-ready output — a latency shift that changes where document parsing can sit in a pipeline.
Why it mattersMedian document processing dropping from 135 seconds to 8 moves agentic PDF extraction — diagrams, charts and form fields included — from a batch job into something you can put behind a live request.
Build AI agents with the Mistral Agents API
Mistral splits agentic use cases out of the Chat Completions API into a purpose-built Agents API.
Why it mattersMistral's Agents API adds a dedicated agent framework alongside chat completions: built-in code execution, web search and MCP tool connectors, persistent cross-conversation memory, and orchestration of multiple agents.
articlemistral.ai
Dwarkesh Patel
Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken
podcast
Listen
Andrew Ng@AndrewYNg
GRPO, the algorithm behind DeepSeek's R1, replaces labeled training examples with Python reward functions — a fit for tasks with verifiable outcomes like math and debugging. It can work with under 100 examples and lifts reasoning in smaller, cheaper models.
Why it mattersReinforcement fine-tuning with GRPO needs reward functions rather than labeled examples and can work with under 100 samples, making reasoning improvements on small models practical without a large dataset.
Devstral
Built with All Hands AI and released under Apache 2.0, Devstral is trained for the scaffolded loop real code agents run in, locating context across a large codebase and fixing actual GitHub issues, rather than for atomic function completion.
Why it mattersDevstral is an Apache 2.0 model trained to resolve real GitHub issues, scoring 46.8% on SWE-Bench Verified and beating far larger models under the same OpenHands scaffold. It is a self-hostable base for code agents.
articlemistral.ai
Launching MCP Servers on Fly.io
The unglamorous parts of shipping an MCP server.
Why it mattersLays out the practical tradeoffs of running MCP servers remotely versus locally — transport choice, per-client config paths, OAuth 2.1 overhead, and the fact that a local server inherits everything you can touch.
articlefly.io
Andrew Ng@AndrewYNg
How the Model Context Protocol removes per-use-case integration work: an MCP client inside the application talks to servers that expose tools, resources and prompt templates, run either as a local subprocess or as a remote process. Plus what building one involves.
Why it mattersExplains MCP's client-server architecture and what a server actually exposes — tools, resources and prompt templates, run locally as a subprocess or remotely — which is the mental model needed before wiring one up.
Coding LLMs from the Ground Up
A ~15-hour video course by Sebastian Raschka that teaches you how to build a large language model from scratch in Python.
Why it mattersIf you want to understand how LLMs work under the hood rather than just calling an API, this ~15-hour course walks you through building one in PyTorch end-to-end — tokenization, attention, pretraining, and finetuning.
articleSebastian Raschka, PhD
Evolution Product Classification
Shopify's product classification moved from TF-IDF logistic regression to vision-language models grounded in a maintained product taxonomy, now serving 30M+ predictions daily for category assignment and attribute extraction across a wildly heterogeneous catalog.
Why it mattersShows what a VLM classification stack looks like in production at 30M predictions a day, and why a hand-maintained taxonomy is the piece that makes model output usable downstream.
articleShopify Engineering
Andrew Ng@AndrewYNg
A LiveKit-built course walking the production voice-agent stack: speech-to-text, text-to-speech and LLM composition, where latency accumulates at each hop, modular pipelines versus speech-to-speech APIs, WebRTC transport, and a cloud deployment serving many concurrent callers.
Why it mattersVoice agents live or die on latency budgets; this maps where the milliseconds go across the stack and when a speech-to-speech API beats a modular pipeline.
Medium is the new large.
Mistral's mid-tier model targets the cost/performance frontier.
Why it mattersMistral Medium 3 is priced at $0.4 in / $2 out per million tokens while claiming at least 90% of Claude Sonnet 3.7 across benchmarks, with hybrid or in-VPC deployment available.
articlemistral.ai
Provisioning Machines using MCPs
Adding volume commands to a cloud CLI's MCP server, then letting Claude find and clean up orphaned volumes on its own.
Why it mattersShows infrastructure provisioning driven through MCP tool calls — an LLM listing volumes, spotting unattached ones, and deleting them — and what that implies for CLI- and Terraform-shaped ops workflows.
articlefly.io
Why We Think
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post.
Why it mattersA carefully sourced deep dive into why test-time compute and chain-of-thought improve LLM reasoning, giving engineers a mental model for when and how to spend inference-time compute effectively.
articleLilian Weng
Dwarkesh Patel
Mark Zuckerberg — AI will write most Meta code in 18 months
podcast
Listen
articleQwen Team
Qwen3: Think Deeper, Act Faster
Qwen3 arrives with the flagship Qwen3-235B-A22B competitive with DeepSeek-R1, o1, o3-mini, Grok-3 and Gemini-2.5-Pro on coding, maths and general benchmarks, alongside smaller mixture-of-experts variants.
Why it mattersQwen3 introduces hybrid reasoning (switchable thinking/non-thinking modes) and open-weight MoE models where a 30B-A3B activates only 3B parameters yet outperforms much larger models.
Andrew Ng@AndrewYNg
Ng argues coding agents are collapsing the value of language-specific syntax: a backend and ML engineer now ships frontend TypeScript. The counterweight he names is conceptual depth — learn one language properly, then let the model translate the concepts into the rest.
Why it mattersA concrete case for working across language boundaries: concepts transfer and syntax is now a prompting detail — but only if you know the concepts well enough to steer with them.
Andrew Ng@AndrewYNg
Hugging Face's smolagents course argues code agents beat sequential tool calls by emitting one executable action block, cutting round trips and failure surface. Covers when that wins, safe execution via a constrained Python interpreter and E2B sandboxing, and tracing to debug the loop.
Why it mattersCode-as-action is a real architectural alternative to function-calling loops, and the difficult piece — sandboxed execution of model-written code — is addressed directly.
An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
Applying the scientific method, building via eval-driven development, and monitoring AI output.
Why it mattersIf you're relying on an LLM-as-Judge to guarantee product quality, this makes the case that the judge is only as good as your process.
articleEugene Yan
Best practices for Claude Code
An Anthropic documentation guide covering patterns for effective agentic coding with Claude Code, including environment configuration and techniques for scaling across parallel sessions.
Why it mattersIt's the canonical, vendor-authored playbook for getting real work out of Claude Code — concrete guidance on CLAUDE.md context files, tool permissions, custom slash commands, and running multiple agent sessions in parallel.
articleAnthropic
Andrew Ng@AndrewYNg
Ng's case against treating evals as a large up-front project: start with five examples and unoptimized metrics, then improve the metrics and the system together, progressively shifting the judging burden off humans and onto automation.
Why it mattersReframes evals as something you start dirty and grow, which is usually the reason teams stay stuck on manual human review of outputs far longer than they should.
Dwarkesh Patel
AGI is still 30 years away — Ege Erdil & Tamay Besiroglu
podcast
Listen
Andrew Ng@AndrewYNg
A course on web agents that reason over both screenshots and DOM structure to act on pages. It centers the compounding-error problem in long action sequences and covers AgentQ's self-correction, with builds that scrape sites, fill forms and chain multi-step tasks.
Why it mattersLong browser action sequences turn a single misclick into a failed task; this attacks that compounding-error problem with self-correction rather than better prompting.
30 Minutes With MCP and flyctl
Wrapping two CLI commands as MCP tools in roughly 90 lines and half an hour, using stdio transport and an off-the-shelf Go library.
Why it mattersDemonstrates how little code an MCP server needs — stdio transport, a Go MCP library, two shelled-out CLI commands — which reframes MCP integration as a small task rather than a project.
articlefly.io
Our Best Customers Are Now Robots
A cloud provider reports that agent harnesses, not people, account for most of its recent growth, and works through the consequence.
Why it mattersAgents are becoming the primary consumers of cloud infrastructure, which shifts the design target from human developer experience to machine-legible APIs, fast provisioning, and disposable environments.
articlefly.io
Andrew Ng@AndrewYNg
Ng's counter to context-maximalism: when you can cheaply judge the result, throw a terse prompt — or just the stack trace — at the model and iterate. He names the conditions where it fails, including specs so partial no competent human could infer the intent either.
Why it mattersGives an explicit rule for how much prompt effort to spend: cheap verification favors terse prompts, while expensive or unverifiable output justifies the long written spec.
Dwarkesh Patel
AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo
podcast
Listen
Andrew Ng@AndrewYNg
A dottxt-built course separating the approaches to schema-conformant LLM output: vendor structured-output APIs, re-prompting libraries such as instructor, and constrained decoding that blocks tokens violating the schema at each step. Built around a social-media analysis agent.
Why it mattersClarifies the tradeoff between re-prompting and constrained decoding: one pays for retries, the other enforces the schema at generation time.
Introducing Runway Gen 4
Runway's Gen-4 holds characters, objects and locations consistent across scenes from one reference image, with no fine-tuning.
Why it mattersCharacter and object consistency across shots from a single reference image, with no fine-tuning, removes the main blocker to using generated video for multi-shot narrative work.
articleRunway editorial sitemap
articleQwen Team
QVQ-Max: Think with Evidence
QVQ-Max is the first full release of Qwen's visual reasoning model, following the QVQ-72B preview, able to analyse and reason over images and video rather than only describing them.
Why it mattersQVQ-Max is a visual reasoning model that doesn't just caption images but analyzes and reasons over image and video content to solve math, programming, and creative tasks.
Andrew Ng@AndrewYNg
Replit's president and DevRel head teach agent-driven building in the cloud IDE — editor, package manager and deploy in one place. The load-bearing advice is Ng's: partition the problem, spec each module, generate and test one at a time, because one-shot prompting fails at app scale.
Why it mattersNames the workflow separating working agentic development from prompt-and-pray: modular decomposition with per-module specs and testing before moving on.
articleQwen Team
Qwen2.5 Omni: See, Hear, Talk, Write, Do It All!
Qwen2.5-Omni is an end-to-end multimodal model that takes text, images, audio and video and responds in real time through both text and natural speech synthesis.
Why it mattersQwen2.5-Omni is an openly available 7B end-to-end multimodal model that perceives text, images, audio, and video while streaming both text and natural speech responses in real time.
A Field Guide to Rapidly Improving AI Products
Most AI teams invest in architecture before measurement. A field guide to improving AI products that starts by asking how you would know whether any of it works.
Why it mattersIf your AI team obsesses over frameworks and vector DBs but can't tell whether changes actually help, this lays out a measurement-first workflow.
articleHamel Husain
articleQwen Team
Qwen2.5-VL-32B: Smarter and Lighter
Qwen2.5-VL-32B-Instruct arrives under Apache 2.0, a reinforcement-learning-refined vision-language model at the community's favorite 32B scale.
Why it mattersQwen2.5-VL-32B-Instruct is an Apache 2.0 vision-language model at a self-hostable 32B scale, refined with reinforcement learning for stronger multimodal reasoning.
The "think" tool: Enabling Claude to stop and think in complex tool use situations
The "think" tool: Enabling Claude to stop and think in complex tool use situations
Why it mattersAdding a no-op 'think' tool gives Claude an explicit checkpoint to reason through policies and multi-step tool chains, measurably improving reliability on complex agentic tasks — a cheap, easy pattern to drop into any agent that uses tools.
articleAnthropic
Andrew Ng@AndrewYNg
LangChain's Harrison Chase teaches memory architecture for agents: semantic, episodic and procedural stores, updated either in the hot path or by a background helper agent. The build is an email assistant that learns user preferences and evolves its own instructions.
Why it mattersA concrete taxonomy for the two decisions agent memory turns on: what to store and retrieve, and whether to update inline or out of band.
An index of the vibe-coding frontier. Corrections welcome.