标签：#context

"Context bombing" tricks hacking agents into shutting down before they can do harm.

DoorDash details the architecture behind Ask DoorDash, its AI-powered conversational shopping assistant, combining LLMs, specialized AI agents, MCP-based tooling, and an intelligence layer with persistent consumer memory and live backend data. Early results show up to 24% higher checkout conversion, 17% larger baskets, and improved intent accuracy using memory-backed sessions. By Leela Kumili

GitHub has made the redesigned GitHub Copilot CLI terminal interface generally available. It adds a tabbed layout for sessions, gists, issues, and pull requests; an in-session, form-driven setup for MCP servers, skills, and plugins that avoids hand-editing config files; and a cleaner, theme-aware, more accessible UI with screen reader support. By Mark Silvester

Over the past week, two narratives have been colliding everywhere I look. On one side, there's panic. AI is expected to replace marketers, engineers, and entire categories of knowledge work almost overnight. On the other, there are quieter but far more consequential signals: enterprise teams discovering their AI infrastructure is burning through API budgets far faster than expected. This isn't because the underlying models are weak, but because the systems built around them are fundamentally inefficient by design. These aren't separate stories. They're the same failure showing up in different places. A conversation with another developer made that gap visible in real time. He argued that auditing a 150,000-line codebase requires feeding the entire repository into a model in one single, massive pass. It's still a common assumption in mainstream tech: that an LLM works like a giant biological brain that you must fully load with raw text before it can begin to think. But that assumption is already outdated. Modern AI systems don't scale through brute-force context. They scale through structure. And that shift changes everything. Key takeaways Bigger context windows did not solve AI. Treating a frontier model as a monolithic processor that re-reads an entire system on every query is wasteful, dilutes attention, and hides bugs under raw volume. ARC-AGI-3 makes the gap stark: frontier models scored under 1% on interactive reasoning tasks that untrained humans solve at nearly 100%. The gap is architecture, not memory. The teams pulling ahead treat the model as one narrow component inside a larger system: intelligent routing, task decomposition, retrieval, and only the minimum necessary context. The next advantage is not the biggest model or the longest prompt. It is the system designed around the model. Prompting was the first generation; systems architecture is the next. The Myth of the Infinite Context Window When context windows expanded into the hundreds of thousands o

LLM agents burn a ridiculous number of tokens on redundancy: opening the same files again and again, trying a patch, failing, then wandering back through the repo like they’ve never seen it before. A July 2026 paper, ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair , puts real numbers behind that waste. In repository-level repair, agents keep dragging in irrelevant code and logs. ContextSniper tackles that with a context layer built around tiered memory and an intention-aware context gate that filters low-value regions before they ever reach the model. That gate alone cut tokens by 51.5% on one host agent and 38.9% on Claude Code, while submitted-resolution rates stayed basically in the same neighborhood. The gate is the interesting part, because it is not tied to that paper’s exact system. It is a more general idea, and it is starting to show up across agent architectures. At heart, the gate is just a classifier. Given a request, it has to decide what kind of retrieval will answer the question cheapest: symbol lookup, semantic search, graph impact, mutation prep, or something else. That leads to the practical question the paper does not really answer: Do you need another LLM call just to decide what context to retrieve? We tested that directly. Five ways agents get code into context Before you can gate anything, you need a retrieval strategy. Most current systems fall into one of five rough families: Grounded read-only retrieval: parse the code and return exact symbol source by name. Byte-precise, no synthesis. Graph code intelligence: model calls, imports, entities, and dependencies as a graph, then traverse it. Embedding / RAG search: use vector similarity over chunks. Whole-repo packers: compress or dump the repo into the context window. Mutate / execute runtimes: retrieve context, then modify or run code. None of these is magic. Graphs are great for relationships, but they can drift away from source. RAG is useful, but f

The Model Context Protocol team has promoted its Enterprise-Managed Authorisation extension to stable status, adding a centralised way for organisations to control access to MCP servers through their identity provider. The project states the aim is to replace per-server consent prompts with a zero-touch flow in which users sign in once and then access approved servers without further setup. By Matt Saunders

DeepSeek has previewed its V4 model family, led by a 1.6 trillion-parameter flagship, and made a one-million-token context window the default across all its services. The weights are downloadable and self-hostable, putting frontier-scale long context in reach of smaller labs and individuals without per-token payment to a closed provider. Key facts What: DeepSeek previewed two free-to-download V4 models that can read a million tokens at once, no longer as a premium add-on but as the standard setting. When: 2026-06-29 Primary source: read the source A large language model has no persistent memory. Each time it answers, it re-reads everything in front of it — your question, the conversation so far, any documents you pasted — and that pile of text is the context. The context window is the hard ceiling on how much it can hold at once. For years that ceiling was a few thousand words, then tens of thousands. Pushing it to a million has been possible but expensive, usually sold as a special, pricey tier. DeepSeek's move is to make a million the everyday default. The family comes in two sizes. V4-Pro is the big one — 1.6 trillion parameters in total, but only about 49 billion of them switch on for any given word. That design is called a mixture of experts : instead of running the entire brain for every token, the model routes each piece of text to a small relevant subset of specialists, so it stays affordable to run despite its enormous size. V4-Flash is the smaller, cheaper, faster sibling, meant for everyday chat and quick edits, and DeepSeek says it keeps up with Pro on simpler agent tasks. Making a million-token window affordable comes down to how the model handles its KV cache — the running set of notes it stores about every previous word, which grows steadily the longer the conversation gets. At a million tokens those notes become a mountain of memory, and the model normally has to consult every note for every new word it writes. DeepSeek's approach, which they call sp

If you run a RAG system in production, you eventually hit a dilemma that has nothing to do with your model and everything to do with your cache. Cache the answers to save tokens and latency, and one day a source document changes — but your cache keeps cheerfully serving the answer it built from the old document. Nobody gets an error. The number is just quietly wrong. Cache nothing , and every single call re-retrieves the same chunks, re-reads them, and re-pays the full context bill to rebuild an understanding you already built five minutes ago for a nearly identical question. Stale or expensive. Most teams pick "expensive" because at least it's correct, then bolt on a TTL and hope. This post is about why the TTL doesn't save you, and about two specific, mechanical fixes that let you cache RAG context and stay fresh. I maintain an open-source library called Coalent that implements both, so I'll use it for the runnable examples — but the two ideas are portable and worth stealing even if you never pip install anything. Failure mode 1: the stale RAG cache (and why a TTL won't save you) Here's the standard "answer cache" sitting in front of retrieval: answer = cache . get ( query ) if answer is None : chunks = retriever . retrieve ( query ) answer = llm . synthesize ( query , chunks ) cache . set ( query , answer , ttl = 3600 ) return answer This works until billing.md changes. The refund window goes from 30 days to 14. Your cache has an answer keyed on "what is our refund policy?" that says 30, and it will keep saying 30 for up to an hour — or forever, if the same question keeps refreshing a TTL that never expires under load. The reason this is hard is that the cache key (the query) has no relationship to the thing that changed (the source). You cached an answer; you threw away the fact that this particular answer was derived from billing.md . So when billing.md changes, you have no way to find the answers that depended on it. The TTL is a confession that you can't answ

X has launched a hosted MCP server, making it easier for developers to connect AI applications with the company’s API.

Elastic open-sourced Atlas, a system built on Elasticsearch that maintains three categories of memory for agents. Atlas integrates with agents via MCP and maintains per-user isolation of memories. When evaluated on question-answering capability, it scored 0.89 Recall@10. By Anthony Alford

The Knowledge Atom: Writing for Machines That Read The Hoarder's Reflex Everyone is learning to feed the machine. Bigger context files. Paste the whole document. "Give the AI all the context it needs." The entire industry has converged on a single instinct: when in doubt, add more. It's the wrong instinct. A context window is not a hard drive. It's a desk. And a desk piled with every document you own is not a well-informed desk — it's an unusable one. The model doesn't read better because you gave it more. It reads worse, because the one line that mattered is now buried under a thousand that didn't. Knowledge an AI can't find is knowledge it doesn't have. Knowledge it always carries is weight it always pays. The Two Failures There are only two ways to get this wrong, and almost everyone commits one of them. The first is the dump . You take everything you know and pour it inline — into the system prompt, the master config, the one document to rule them all. It feels thorough. It is the opposite. Every token you add dilutes every token already there. Signal drowns in completeness. The model now has all the knowledge and none of the focus. The second is the orphan . You did the disciplined thing. You wrote a clean, perfect note, in its own file, out of the way. And then nothing pointed to it. No index, no trigger, no path back. The note is immaculate and invisible — which is worse than never writing it, because you believe the knowledge is in the system when in fact it is dead. Both failures share one root: confusing having knowledge with retrieving it. Same Pattern, New Sauce Watch the field long enough and you'll see the same thing return, repainted each time. The "Ralph Wiggum" loop becomes "the agentic loop." Agent teams that talk to each other become a single orchestrator, and then an agent that makes other agents talk to each other. Every cycle sells itself as the breakthrough. Every cycle is a re-skin of the last. Underneath the churn, only one thing actually ch

Vercel has released Eve, an open-source framework for building, deploying, and operating AI agents in production. The framework uses a filesystem-based project structure to organize agent instructions, tools, skills, subagents, communication channels, and scheduled tasks, enabling developers to define agent behavior while reducing the amount of supporting infrastructure they need to implement. By Daniel Dominguez

This is an adapted English version of an article I first wrote in Japanese. I work with AI to shape and review my drafts, but the argument and the field observations are my own. The numbers are cited from public surveys (linked at the end). I built an aggressive prompt-injection block to stop my AI agent from repeating the same mistakes. It worked, so I kept adding rules. By the time I noticed, the file had ballooned to 56,000 characters — and the agent had quietly stopped functioning. Too much context, attention spread too thin to act on any of it. I gutted it back to under 1,200 characters, and here's the part that still stings: it behaved better with fewer rules. That was the day I learned my whole mental model was backwards. This isn't a post about making your AI more accurate. It's about designing so that accuracy stops being the thing you depend on. The mistake I made for months My agent kept skipping the same step in a workflow. So I did what every engineer does on instinct: I added a rule. "Don't skip this step." Then it did something else dumb, so I added another rule. Then another. I was treating the rules file like a conversation with a colleague — as if the agent would remember yesterday's correction and carry it forward. It doesn't. Every run starts cold. "Be careful next time" assumes a next time that shares state with this time. For a stateless model, there is no continuity to appeal to. You are talking to a counterparty with no memory of the conversation you think you're having. So the rules pile up, because each correction feels like progress. And for a while the numbers even improve. But adding rules has a ceiling, and I blew straight through it: at 56,000 characters the agent wasn't reasoning over my guardrails anymore — it was drowning in them. Knowing a rule and stopping at it are different things Here's the distinction that took me far too long to see. Putting a rule in the context window means the model knows the rule. It does not mean the mod

Most agents drag their entire past into every turn. A better default: keep a thin index of what was said hot, and fetch only the few turns you actually need — intact, on demand. Code: github.com/NirajPandey05/jit_context There is a quiet assumption baked into how most agents handle memory: that more context is safer than less. If the model might need something, put it in the window. The conversation grows, every prior turn rides along on every new request, and we trust the model to find the part that matters. That assumption breaks twice. It breaks on cost , because an agent loop re-sends its whole window on every step — a hundred stale turns aren't paid for once, they're paid for on turn 101, 102, and every step after. And it breaks on quality , because models don't read a long window evenly. Relevant facts buried in the middle get underweighted; irrelevant bulk competes for attention with the thing that actually answers the question. Past a point, a bigger context produces a worse answer, not just a costlier one. So the interesting question isn't "how do we fit more in?" It's "how do we keep the window small and dense without losing the one old turn that matters?" This post is the design we built around that question — for the specific case of long conversation history — plus the benchmark we used to keep ourselves honest. 01 · The mechanism: a hot index over a cold store The design borrows directly from how computers have always managed memory that doesn't fit: a small fast tier that's always present, a large slow tier that holds the bulk, and a rule for moving things between them. Virtual memory pages between RAM and disk. We page between the context window and an external store — for attention instead of address space. Concretely, there are two tiers. The cold store holds every turn at full fidelity, keyed by id — nothing is thrown away. The hot index holds one compact entry per turn: a short summary, a little metadata (entities, whether the turn recorded a dec

Your repo is already your agents' context, whether you designed it on purpose or not That sentence took me a while to understand. In this post I'll save you the trip. It was October 2025, working in Skyward's monorepo with AI agents every day. And every day the same routine: I'd tell the agent in the prompt "don't use this", "don't do it this way", "reuse the component that already exists". I wrote it down. I repeated it. The agent did exactly what I told it not to do. It wasn't that it didn't listen to me. It was that it read the code and saw something else there. The agent believes the code, not your prompt An agent follows the patterns it sees in the repo, not the ones you tell it in the prompt. And subagents are worse, because they start without the conversation's context. The whole fight you put up earlier in the chat, for them it never happened. So this is what kept happening. It created a new component even though one already existed that solved exactly that problem. It didn't respect the design rules or use the design tokens. It followed stale docs because they were still there, alive, with nothing flagging them as outdated. My first instinct was everyone's instinct, cram more context into the prompt. More rules, more "please don't do this", more examples pasted in by hand. It half worked, and for the next task you had to add it all again. Until the next subagent showed up and started from scratch. At some point, tired of repeating myself, I understood the obvious thing. The agent wasn't disobeying me. It was reading the repo and listening to what the repo said about itself. If the good component lives alongside three old versions, it has no way to know which one is the official one. If the docs say one thing and the code does another, it'll believe whichever is closest at hand. It's doing exactly what I asked. The repo itself is the context agents use. If it's badly structured, the answers won't be good. Period. No prompt fixes a repo that contradicts itsel

Tu repo ya es el contexto de tus agentes, lo hayas diseñado a propósito o no Esa frase me costó entenderla. En este post te ahorro el camino. Era Octubre del 2025, trabajando en el monorepo de Skyward con agentes de IA todos los días. Y todos los días la misma rutina: le decía en el prompt al agente "no uses esto", "no hagas esto así", "reutiliza el componente que ya existe". Lo escribía. Lo repetía. El agente hacía exactamente lo que le dije que no hiciera. No era que no me escuchara. Era que leía el código y ahí veía otra cosa. El agente le cree al código, no a tu prompt Un agente sigue los patrones que ve en el repo, no los que tú le dices en el prompt. Y los subagentes son peores, porque arrancan sin el contexto de la conversación. Toda la pelea que tú diste arriba en el chat, para ellos no existió nunca. Entonces pasaba esto. Creaba un componente nuevo aunque ya había uno que resolvía exactamente el problema. No respetaba las normas de diseño ni usaba los design tokens. Seguía documentación obsoleta porque seguía ahí, viva, sin nada que la marcara como obsoleta. Mi primer instinto fue el de todos, meter más contexto en el prompt. Más reglas, más "por favor no hagas esto", más ejemplos pegados a mano. Funcionaba a medias, y para la siguiente tarea había que volver a agregarlo todo. Hasta que llegaba el siguiente subagente y empezaba de cero. En algún momento, cansado de repetirme, entendí lo obvio. El agente no me estaba desobedeciendo. Estaba leyendo el repo y haciendo caso a lo que el repo decía de sí mismo. Si conviven el componente bueno y tres versiones viejas, no tiene cómo saber cuál es el oficial. Si la doc dice una cosa y el código hace otra, le va a creer al que esté más a mano. Está haciendo justo lo que le pedí. El mismo repo es el contexto que usan los agentes. Si está mal estructurado, las respuestas no van a ser buenas. Punto. No hay prompt que arregle un repo que se contradice a sí mismo. Screaming Architecture me llevó hasta media cancha Lo prim

On June 12, 2026, enterprise developers using the Codex API started seeing an unfamiliar response header: X-Model-Version: kindle-alpha . It appeared on a subset of requests for roughly 18 hours, then vanished. That's the release candidate for GPT-5.6 — OpenAI's next flagship model — leaking through the staging layer. OpenAI's Chief Scientist publicly called the upcoming release "a meaningful leap" the following day. By OpenAI's historically understated communications standards, that's loud. This post covers what the backend traces, developer reports, and Polymarket odds (currently ~80% for a pre-June-30 launch) actually tell you about the model — and what to do before it drops. How the Leak Surfaced Three separate sources converged in the 72 hours after the June 12 header incident. First, developers with ChatGPT Pro OAuth access reported hitting context windows significantly beyond GPT-5.5's supported limit. At least four documented cases logged successful 1.5M-token completions before the backend silently downgraded them to the production model. Second, the Codex enterprise API logs — accessible with full response header exposure enabled — confirmed the kindle-alpha codename across US-east-1 and us-west-2 endpoints. Third, the Polymarket market for "GPT-5.6 public release before July 1, 2026" moved from 61% to 80%+ within 48 hours of the header reports circulating on developer forums. None of this is from OpenAI's press office. No model card, no official benchmark numbers, no pricing. The specifics below are high-confidence inference from multiple corroborating signals — not official spec. Treat it accordingly when making production decisions. The Architecture Shift: Agentic-First, Not Just Smarter GPT-5.5 was trained as a reasoning model with agent capabilities added on top. GPT-5.6 is reportedly designed in the opposite order. The primary optimization target during training was not MMLU or GPQA benchmark scores — it was token efficiency on long-horizon agentic t

Uber recently described an internal architecture for propagating identity across multi-agent AI workflows. The design aims to perserve user context, agent provenance, and scoped access as agents delegate work and call internal tools. The case study aligns with Auth0’s view that AI agents need permissions based on delegated authority, scoped credentials, and explicit human approval boundaries. By Eran Stiller

HashiCorp has announced the general availability of the Terraform MCP Server, an open-source MCP server that enables agents to integrate with Terraform Registry APIs. The company says that it can improve infrastructure teams productivity by relieving engineers of rote tasks. By Sergio De Simone

Model Context Protocol (MCP): Giao Thức Kết Nối Thế Giới Cho Trí Tuệ Nhân Tạo Trong thế giới AI đang phát triển với tốc độ chóng mặt, việc xây dựng các ứng dụng thông minh, có khả năng tương tác linh hoạt với dữ liệu và công cụ bên ngoài là một thách thức lớn. Các mô hình ngôn ngữ lớn (LLM) như GPT, Claude, hay Gemini dù mạnh mẽ nhưng thường hoạt động trong "vùng cô lập", thiếu khả năng truy cập trực tiếp vào các hệ thống bên ngoài theo thời gian thực. Đây chính là lúc Model Context Protocol (MCP) xuất hiện như một giải pháp cách mạng. MCP là một giao thức mở, được thiết kế để tiêu chuẩn hóa cách thức các ứng dụng cung cấp ngữ cảnh (context) cho LLM, giúp phá vỡ rào cản giữa trí tuệ nhân tạo và thế giới thực. Bài viết này sẽ đi sâu vào phân tích Model Context Protocol , từ định nghĩa, kiến trúc, đến các lợi ích và ứng dụng thực tế, giúp bạn hiểu tại sao nó được coi là "ngôn ngữ chung" của tương lai AI. Model Context Protocol (MCP) Là Gì? Model Context Protocol (MCP) là một giao thức mở, được phát triển để tạo ra một chuẩn giao tiếp thống nhất giữa các LLM và các nguồn dữ liệu, công cụ bên ngoài. Hãy tưởng tượng MCP như một "cổng USB" dành cho AI. Thay vì mỗi ứng dụng AI phải viết mã tích hợp riêng lẻ với từng loại cơ sở dữ liệu, API, hay hệ thống tệp tin (mỗi loại một kiểu "phích cắm" khác nhau), MCP cung cấp một giao diện chuẩn. Bất kỳ ứng dụng nào hỗ trợ MCP đều có thể kết nối với bất kỳ nguồn tài nguyên nào cũng hỗ trợ MCP một cách liền mạch. Mục Đích Cốt Lõi Của MCP Mục tiêu chính của Model Context Protocol là giải quyết vấn đề "fragmentation" (phân mảnh) trong hệ sinh thái AI. Trước MCP, việc tích hợp thường diễn ra rời rạc: Mỗi nhà phát triển ứng dụng phải tự xây dựng các "kết nối" tùy chỉnh. Mỗi lần cập nhật mô hình hoặc công cụ có thể làm hỏng các tích hợp cũ. Khó khăn trong việc chia sẻ và tái sử dụng các công cụ AI giữa các dự án. MCP giải quyết những vấn đề này bằng cách cung cấp một lớp trừu tượng chuẩn hóa. Kiến Trúc Và Cách Thức Hoạt Động Của MCP Kiến