标签：#AI

Anthropic’s Claude Sonnet 5 brings stronger agentic capabilities, lower pricing, and improved safety, positioning the model as a cheaper alternative to Opus, GPT-5.5, and Gemini Pro.

Artificial Intelligence is rapidly evolving from chatbots to autonomous agents capable of...

Acti is betting the smartphone keyboard is the next home for AI assistants. The startup's new keyboard for iOS and Android works across apps and lets users create custom AI-powered shortcuts using natural language.

A new teaser trailer confirmed that Wonka's The Golden Ticket will premiere on Netflix on September 23rd, following its Squid Game reality show in the trend of creating real competitions based on fictional torture scenarios. While the sets seen in the trailer are real and not some Glasgow-style AI fakes, the voiceover is AI-generated. Deadline […]

Anthropic's Claude Science is a workbench that gives scientists one environment to do computational research, saving them from the need to bounce between databases, pipelines, and tools.

A year in, National Design Studio delays plan to update government web standards.

Last week we introduced Upsun Dispatch™: a platform for the agentic software development lifecycle, where workflow is the primitive , not the agent. Today, prerelease is open. Starting July 1, a founding cohort of design partners gets early access. This is not a traditional beta. We are looking for engineering teams already running AI workflows and hitting the limits of what individual tools can do: teams who want to help shape what Upsun Dispatch becomes, not just use what we ship. Design partners get direct access to the core team, real input on the roadmap, and charter terms that reflect a genuine partnership rather than a vendor relationship. Apply at upsun.com/dispatch . Read the full announcement: Upsun Dispatch™ is now open for prerelease Starting July 1, 2026, Upsun Dispatch™ is open to a founding cohort of design partners. Here is what joining early means and how to apply upsun.com

Sources suggest Musk may be mulling big donation to Trump Accounts.

I was taking a break from the AIE Workshops on Monday and stepped out by the food stands to check out the crepes. That's when I saw a line literally wrapping the entire length of the Moscone West windows looking out onto Fourth Street. I couldn't imagine what a several-hundred-person line was for, and when I went to ask, they told me it was for the Context Engineering Workshop. That sent me down a rabbit hole exploring and understanding and learning. So now, for you, I will share what I got. For the past couple of years, the AI world was obsessed with prompt engineering, aka the art of speaking to a machine. But as developers move from simple chatbots to complex autonomous agents, a new discipline has taken center stage: context engineering. Mike Swift ( @theycallmeswift ), CEO of Major League Hacking ( @mlhacks ) , gave me some critical background. He pointed me to Dex Horthy of HumanLayer (who is actually speaking later this week), who basically coined the term at the first AI Engineer World's Fair. Dex's core thesis, said Swift, is that "agents get bad after about 100,000 tokens," which represents roughly 10% of their total available context window. So context engineering is essentially managing an AI's working memory. Context engineering, Swift noted, is "managing how many times the loop goes around to how much you have to remember every time you do it." It is a counterintuitive concept for humans; the more we talk about a subject, the deeper our shared understanding becomes. But models work the opposite way. They lose focus as their context window fills up. For many developers, meticulously curating this working memory is a practical necessity. I sat down with Ben Halpern ( @ben ), founder in residence at MLH and co-founder of DEV, who told me that context engineering is the "latest frontier of the optimization point" where developers can leverage their expertise. Beyond just keeping models coherent, Ben pointed out that developers who are doing product work ma

This is Lowpass by Janko Roettgers, a newsletter on the ever-evolving intersection of tech and entertainment, syndicated just for The Verge subscribers once a week. "AI is the new frontier for us," says Marc DeBevoise, who took over as the new CEO of OverDrive last week. OverDrive is best known for the ebook lending app […]

You have seen this loop before. An agent starts a “simple” task, say scrape listings, refactor a repo, research a market, or whatever. It fails, it retries, it re-reads context, it apologizes and tries all over again. Twenty minutes in and the dashboard shows six figures of tokens and zero useful outputs or deliverables. The model did not misbehave on purpose. The orchestrator never had a hard budget gate with an ROI in mind. Skillware v0.4.0 ships a new skill for exactly that gap: monitoring/token_limiter . It lets you monitor and limit any agent’s token budget in real time — Gemini, Claude, OpenAI, DeepSeek, Ollama, custom Python loops, you name it. Same skill, same JSON, any runtime. What Skillware is in a nutshell Skillware is an open registry of installable agent capabilities . Each skill is a bundle: skill.py — deterministic Python ( execute() returns JSON) instructions.md — when the model should call the tool manifest.yaml — schema, constitution, issuer Tests and docs — shipped in the wheel You load by ID, adapt for your provider, call execute() on tool use. The model decides when , the skill decides how , predictably, every time. That split matters for budget control. You do not want the LLM guessing whether it is “allowed” to spend more tokens. You want a small, auditable function that answers: continue, warn, or stop. Meet the Token Limiter This skill is a budget gate , not a kill switch wired into OpenAI or Anthropic. After each model turn, your host loop passes cumulative usage. The skill returns one of three actions: Action Meaning CONTINUE Under the soft threshold — keep going WARN Approaching the limit (default 80%) — tighten scope FORCE_TERMINATE Hard ceiling hit — stop the loop Important nuance: the skill does not cancel API sessions or kill processes. It returns a structured decision. Your orchestrator must act on it. That is by design — Skillware skills stay portable and provider-neutral. No skill-specific API keys. No network calls. Pure Python m

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

Engineers on the new team will embed within companies to deploy purpose-built agents, focusing on fast deployments and customer self-sufficiency.

Users will be able use AI to create newsletters based on their recordings.

You can use Gemini to quickly search your Gmail inbox with natural language.

Yesterday, we kicked off our physical newspaper, The Daily Context, at the AI Engineer World’s Fair...

Proton's Lumo 2.0 is dropping this week, giving users a broader variety of capabilities.

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

Hi, I’m David. I’m close enough to middle age that I have no interest in pretending I discovered the future of software development in a week. What I did do was spend one serious week building a small local app with AI assistance, while trying to keep the project understandable. That turned out to be harder, and more interesting, than I expected. The coding agent could move quickly. Sometimes very quickly. It could generate code, refactor, write boilerplate, and help move the project forward. But it could also widen scope, preserve the wrong assumption, “helpfully” redesign something I wanted to keep boring, or act on context that was never meant to become implementation work. The main lesson I took from that week was simple: AI-assisted development is not only a coding problem. It is a context management problem. So I started using a lightweight loop: Task Brief -> think through the problem Codex Contract -> give the coding agent a bounded instruction set Final Review -> test, inspect, patch, and update project memory The result was not perfect AI coding. The result was reviewable AI coding. That distinction felt important enough to write down. The three articles I published three companion articles from that first week. They are meant to stand on their own, but together they describe the workflow, the memory system, and the objections I think are worth taking seriously. 1. Vibe Coding Done Right This is the accessible starting point. It explains how I used a lightweight, spec-driven workflow as a solo developer working with ChatGPT, Codex, VS Code, PowerShell, and a local LLM through LM Studio. The point is not the exact stack. The point is the separation: one place for thinking, learning, and review; another place for bounded implementation; documentation as the memory that keeps the next task grounded. 2. Documentation as Project Memory in AI-Assisted Development This is the more technical case-study piece. The part that surprised me most was documentation. Not

Cost is everything. In just about every agentic conversation, the three things that come up for enterprises implementing AI workloads are: Cost Observability Security and as AI continues to throw everyone for a loop when it comes to cost management (e.g - Uber running out of the yearly token budget in one quarter), the ability to shrink resource (like hardware) usage will be crucial moving forward. In this blog post, you will learn how to cust costs by 90% using Agent Susbtrate in comparison to Agents running in k8s Deployments/Pods. The Cost Comparison Agents need a place to run. The "place to run" needs to be a platform that's easily managed, orchestrated, and has the ability to cluster resources. Resources like CPU, GPU, and memory need to be able to scale and expand. Without this, it's a matter of manually managing servers that Agents are running on and clients to interact with said server. That's why so many organizations choose Kubernetes to run Agentic. When running Agents per Pod, however, that can get costly very quick in terms of hardware (GPU, CPU, memory) and performance (can your cluster scale up and down quickly based on resource needs when it comes to Agents coming up and going down per use?). The tests in this blog post show: Always-on Agents running in k8s. Actors running in Workers via Agent Substrate And the comparison will be 50 always-on Pods in comparison to 50 Actors across 5-7 Workers (Pods). If there are 50 Agents running per Pod and 50 Agents running per Worker with 5-10 Actors per Pod, you can already imagine the hardware resource savings that can be accomplished. Right now, the majority of organizations start off with the "one Agent per Pod" approach as that's the fastest way to show value and get up and running. For the future, however, Agents in Actors via Agent Substrate will be how organizations deploy when they care about efficiency, optimization, and managing cost. Let's dive in from a hands-on perspective. Prerequisites To follow a