标签：#ai

If you've run more than one AI coding agent on the same project, you already know the failure mode. You point Claude Code at /src/game and Cursor at /src/ui "just to be safe," and twenty minutes later one of them has quietly rewritten a file the other was mid-edit on. No error, no warning — just a diff that makes no sense and an afternoon spent figuring out which agent ate whose work. The agents aren't the problem. The problem is that multiple AI coding agents on the same codebase have no shared notion of "someone else is touching this file right now." Each one acts as if it's alone, and that assumption breaks the moment you run two, three, or four in parallel — exactly when a solo builder or vibe-coder would want to, to ship faster. I built Bothread to fix this. It's free, open-source, and runs entirely on your own machine. Why AI Coding Agents Overwrite Each Other's Files The core issue is coordination, not intelligence. One agent working alone is usually fine. Trouble starts when a second agent, unaware of the first, opens that same file and writes its own version on top. Whoever saves last wins, silently — no lock, no claim, no message saying "I'm in physics.js , give me five minutes." Multiply that by however many agents you're running and you get the pattern anyone doing multi-agent AI coding eventually hits: duplicated work, clobbered edits, and a human reconstructing what happened after the fact instead of watching it happen. Bothread's answer: give the agents a shared room, over MCP (Model Context Protocol) , where "who's working on what" is a fact everyone can see and act on — not something you guess at after a merge conflict. What Bothread Actually Does Bothread is a small local server (no cloud, no accounts) that any MCP-compatible agent can join as a participant in a shared room: Claim files before editing — a claim on a file someone else already holds gets denied and shown, instead of silently overwritten. Talk in a live thread , share a task board and

Spotify is experimenting with a new AI feature that allows Premium subscribers to play and explore music, audiobooks, and podcasts by having conversations with a chatbot. The "Talk to Spotify" feature appears across the Home and Now Playing view on Spotify's mobile app. You can interact with the chatbot by typing your request in the […]

I had a tidy little helper that computed a thinking budget based on input size. Something like "give the model 30% of the context as thinking room." It worked great on Opus 4.5. Then I tried to point it at Opus 4.8 and got a 400. The whole concept I had built around is gone in the current models. Here is what replaced it and how I migrated. What broke The old pattern looked like this: // Opus 4.5 and earlier const response = await client . messages . create ({ model : " claude-opus-4-5 " , max_tokens : 16000 , thinking : { type : " enabled " , budget_tokens : 8000 }, messages , }); On Opus 4.7, 4.8, and Fable 5, thinking: { type: "enabled", budget_tokens: N } returns a 400. The fixed token budget is dead. The replacement is adaptive thinking, where the model decides how much to think, plus an effort knob that controls overall token spend. // Opus 4.8 const response = await client . messages . create ({ model : " claude-opus-4-8 " , max_tokens : 16000 , thinking : { type : " adaptive " }, output_config : { effort : " high " }, // low | medium | high | xhigh | max messages , }); Why this is actually better (after I got over it) My old budget code was a guess dressed up as a calculation. I had no real basis for "30% of context." I picked it because it felt reasonable and the outputs looked fine. Adaptive thinking moves that decision to the model, which sees the actual problem. The mental model shift: budget_tokens controlled how much the model could think. effort controls how much it thinks and acts . They are not the same axis, so there is no clean 1:1 mapping. I stopped trying to translate "8000 tokens" into an effort level and instead picked based on the workload. How I chose effort levels After running my own evals, here is where I landed: Workload Effort Notes Classification, routing low Fast, scoped, not intelligence-sensitive Most app traffic medium to high The balance point Coding and agentic loops xhigh Best for these; it is the Claude Code default Correctness

Build a Local LLM Chatbot with Ollama and Python Build a Local LLM Chatbot with Ollama and Python Imagine typing a question into your chatbot and getting a response in milliseconds, completely offline, with zero data leaving your machine. No API keys, no monthly subscription fees, and no privacy concerns about your data being sent to a cloud server. This isn’t a futuristic dream—it’s the reality of running a Local Large Language Model (LLM) on your own computer. With the rise of tools like Ollama , building a private AI chatbot in Python has become as simple as installing a few packages and writing a short script. Let’s dive in and build one together. Why Go Local? Before we write any code, it’s worth understanding why running an LLM locally is a game-changer. Cloud-based AI services like OpenAI or Anthropic are powerful, but they come with trade-offs: you pay per token, your data is processed on their servers, and you’re dependent on their uptime. A local LLM flips this model. You download the model once, run it on your hardware, and you have full control. Ollama is the engine that makes this accessible. It’s a lightweight, open-source tool that simplifies running LLMs like Llama 3, Phi 3, or Mistral on macOS, Linux, and Windows. It handles model downloads, memory management, and inference, exposing a simple API that Python can easily interact with [1][2]. Step 1: Install Ollama and Pull a Model The first step is getting Ollama on your machine. Visit ollama.com , click Download , and install the version for your operating system [2]. Once installed, verify it’s working by opening your terminal or Command Prompt and running: ollama --version If you see a version number, you’re ready to go. Next, you need a model. Ollama supports dozens of open-source models, but for a beginner-friendly chatbot, Llama 3.2 is a great choice. It’s small, fast, and surprisingly capable. To download it, run: ollama pull llama3.2 This command fetches the model and stores it locally. Depen

It's not abnormal for projects to go weeks, or dare I say months, between dependency updates. And when people finally do update, they do it in full force: everything at once, without checking anything. That habit has always carried risk, but in the new world of AI agents doing the updating, it collides head-on with a very real threat: supply chain attacks. The problem: install is an arbitrary code execution feature The package ecosystems we all depend on have spent the last few years demonstrating exactly how bad this can get. In September 2025, chalk and debug , part of a batch of eighteen packages with over two billion combined weekly downloads, started shipping a crypto-clipper after one maintainer's npm account was phished through a fake 2FA-reset email. Days later, the Shai-Hulud worm chewed through hundreds of packages on its own: its post-install script stole npm tokens from every machine it landed on and used them to publish more infected versions of itself. And a couple of weeks before either, the Nx compromise put a post-install payload on developer machines that prompted locally installed AI coding CLIs like Claude and Gemini to hunt down wallets and credentials for exfiltration. That last one should make every agent owner sit up straight: our own agents, conscripted as burglars. The pattern is consistent: a malicious version goes live, does its damage for a few hours or days, then gets caught and pulled. Based on this, I decided, not to do updates till a set of rules have been met. These rules, I have decided to burn them into Claude skills and let my agents deal with them. AI Agent Skills: paranoia as a config file In Claude Code, a skill is just a markdown file with instructions the agent loads when a task matches. This gives me way to encode my hard-won paranoia once and have it applied every single time , by something that never gets tired, never gets sloppy on a Friday afternoon, and never thinks "eh, it's probably fine." I wrote two of them, for no

New York has become the first state to temporarily halt approval of large data centers, as Gov. Kathy Hochul argues the AI-driven building boom shouldn’t come at the expense of higher electricity costs, water supplies, or local control.

New York’s data center moratorium may become the blueprint for anti-AI movement.

Reflection AI has signed a $1 billion deal to access Nebius' compute. Reflection was founded in 2024 and is developing open source AI technology.

Hugging Face CEO Clem Delangue says enterprises increasingly want open models, due to cost, accessibility, and ownership. Do frontier models still matter if most production AI ends up running on open models?

Spotify is rolling out a new AI-powered conversational feature that lets Premium subscribers chat with the app to discover music, podcasts, audiobooks, and more.

OpenAI has spent the better part of the year involved in lawsuit after lawsuit, including one from the world's richest man. But last Friday, the company was hit with one of the highest-profile legal actions yet - from Apple. OpenAI's expensive hardware bet is what's on the line. Apple's lawsuit against OpenAI, filed in Northern […]

Superhuman’s latest AI email drafting feature is its most convincing yet, generating replies that often required little to no editing in our testing.

Google and industry partners announced Agentic Resource Discovery (ARD) Specification, an open standard for publishing, discovering, and verifying AI tools, APIs, and agents. ARD introduces a discovery layer built on catalogs and registries, enabling dynamic capability discovery while leveraging existing protocols such as MCP and OpenAPI for execution and emphasizing trust and interoperability. By Leela Kumili

Meta recently open-sourced Brain2Qwerty v2, a noninvasive Brain–Computer Interface (BCI) that can decode sentences from thoughts using electroencephalography (EEG) or magnetoencephalography (MEG) signals from the brain. In evaluations, the system achieved a word accuracy rate 61% on average, compared to 8% for other non-invasive methods. By Anthony Alford

Live-service games and the companies that run them are in big trouble. Games and their developers are getting shut down and gutted, and publishers' huge promises are dubious. Meanwhile, EverQuest, one of the original live-service games, is thundering back more than 25 years later. EverQuest Legends is currently in preorder beta with an upcoming release […]

Many enterprise AI governance discussions start with frameworks. Frameworks are useful. They help organizations define principles, roles, controls and accountability. But when an enterprise starts using generative AI in real workflows, the practical governance problem often appears somewhere much more specific: the AI access path. That is the moment when an employee, application, copilot, agent or API workflow sends a request to an AI model. At that point, governance becomes operational. The practical governance questions Before an AI request reaches a model, an enterprise may need to answer several concrete questions: Who is sending the request? What business use case is involved? What data is being sent? Which AI model is being used? Is the model approved for this use case? Should sensitive data be masked or blocked? Was the access decision recorded? Can the activity be reviewed later? Can AI usage and token cost be explained by user, department, model and use case? These questions are not only policy questions. They are architecture questions. If the enterprise cannot answer them at the access path, AI governance may remain too far away from the real system behavior. Why the access path matters Many organizations already have AI policies. But policies are often written before or after the actual AI interaction. The access path is where policy meets execution. For example, a team may approve the use of generative AI for internal productivity. But the organization still needs to understand: whether customer data is being included in prompts; whether employees are using approved or unapproved models; whether sensitive content is being sent to external services; whether different departments are using AI in very different ways; whether audit evidence exists when an incident or review happens. This is why AI governance should not only be treated as a document, committee or training program. It also needs a technical control point. A simple access governance pattern A

Everyone can generate a website now. Type a prompt, get a decent page — that part is a commodity. The question nobody's answering is what happens on day 2 : the leads start arriving, a line of copy needs a tweak, someone asks for a section you forgot. That's when a website stops being a design project and becomes a thing you have to run — and where most tools hand you yet another dashboard to log into and dread. Sitelas makes a different bet. Because a Sitelas site lives inside Claude through an MCP connector, the same chat that built the site also runs it . You don't open an admin panel to see who filled out your form, write back, or change the page. You just ask. Here's what "running your site from a chat" actually looks like. First, the 30-second why Claude connects to outside tools through MCP connectors — you already use the ones for Gmail, Calendar, and Drive. Sitelas has one too. Add it once (in claude.ai: Customize → Connectors → Add custom connector , and paste https://sitelas.com/api/mcp ), and Claude can do things with your site, not just talk about it: publish it, read its submissions, restyle it, add a section. Your site becomes an automation endpoint sitting next to your other connectors — the thing a Webflow or Squarespace site can't be. New here? Start with How to Build a Website From a Claude Chat . "Did anyone fill out my form today?" That single question is the whole idea. You ask; Claude reads your site's submissions, surfaces the new lead — Maya, a bakery owner — and drafts a warm reply in your voice. One message, no tabs. It works because every form on a Sitelas site captures submissions to your inbox automatically — no integration required. You can open that inbox in the dashboard any time: …but running your site from a chat means you rarely need to. Claude reads those same submissions straight from your site, so "who wrote in today, and what do they want?" is answered in the thread you're already in — not in a panel you have to remember to ch

My CLAUDE.md has one line near the bottom that I wrote months ago and mostly forgot about until I started actually paying attention to what it does: ## Important Note after your work done codex will review what you done. Terse, no punctuation, clearly typed in a hurry. But it's a real instruction that fires on every session in this repo: I finish a change, and a second model reviews it before I consider the work done. I added it half as an experiment. A few months in, it's changed how I work more than almost anything else in the setup, and not in the way I expected. I thought it would catch bugs. Mostly it doesn't, not directly. What it actually does is force a triage decision on every single piece of feedback, and getting that triage wrong is where all the pain lives. The three buckets Early on I treated every review comment the same way: read it, do it. That lasted about a week before I was silently making changes I didn't agree with because a second AI suggested them, and separately burning a stupid amount of time re-litigating comments that were just wrong or out of scope. What actually works is sorting every comment into one of three buckets before touching code: Fix it, no discussion. The comment is unambiguous, low-risk, and doesn't touch anything architecturally significant. Just do it and move on. Ask first. The comment is ambiguous, or it touches something that would require a real judgment call, or the "fix" would be a bigger refactor than the comment implies. Stop and get a human decision before acting. Skip silently. The comment is a duplicate of something already handled, or genuinely doesn't apply. Don't reply just to say "not doing this," don't leave a comment thread as evidence of having read it. Silence is the correct response to a non-issue. The failure mode I kept falling into before I had these buckets explicitly was collapsing 2 into 1: treating "ambiguous" as "just pick an interpretation and go." That's the actual source of review fatigue, not

Introduction “When I use a word,” Humpty Dumpty said in rather a scornful tone, “it means just what I choose it to mean—neither more nor less.” “The question is,” said Alice, “whether you can make words mean so many different things.” “The question is,” said Humpty Dumpty, “which is to be master—that's all.” — Lewis Carroll, Through the Looking-Glass Humpty Dumpty believes that words can mean whatever we choose them to mean. Alice asks an interesting question. Can they? Programming and Language Programming languages derive much of their power from formally specified semantics. The language implementation, not the programmer, defines what if , while and return mean. I cannot persuade the compiler that false should be treated as true . The rules establish a shared and mechanically enforced understanding of what a program means. Large Language Models however, do not execute according to fixed semantics. They interpret natural language through context. This distinction has profound consequences and suggests that a language model has no intrinsic notion of authority. In a programming language, when two instructions conflict, the language specification and execution environment determine the outcome. In natural language, authority does not arise from the words alone. It depends on context, convention, identity, and external rules. Language models, by nature, inherit this ambiguity. A prompt is therefore not a program in the traditional sense. It is an attempt to establish the context within which subsequent language should be interpreted. "You are a detective." "Do not reveal the identity of the murderer." "Only answer questions using the evidence you have observed." None of these statements is mechanically enforced merely because it appears in the prompt. They describe a role, a constraint, and an assumed world. The model may follow them, but their authority must be created and protected by systems outside the model. Prompt injection exploits precisely this weakness. It

If you want to stream local media, this free and open source media server is just as good as Plex. But if you rely on remote access or live TV, prepare to tinker.