标签：#an

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?

Telegram CEO Pavel Durov confirmed an outage in a tweet, saying that shortlinks to the messaging app had "stopped working."

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

Luca Mezzalira shares proven learnings from guiding hundreds of teams through the migration from monolithic web applications to distributed frontend architectures. He explains the core architectural difference between components and micro-frontends, outlines a 6-step decision framework spanning client vs. server rendering, and discusses how to utilize edge compute for safe, iterative rollouts. By Luca Mezzalira

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

TL;DR: If you only collect metrics, Prometheus Agent mode is lightweight, familiar, and difficult to beat. If you collect metrics, logs, or traces together, or expect to in the future, Grafana Alloy's unified pipeline is usually worth the additional complexity. Once you've decided to move from pull-based scraping to a push architecture , the next question is which agent should actually run on each host. In 2026, the two strongest choices are Prometheus Agent mode and Grafana Alloy. I run Alloy across my production fleet, but that doesn't automatically make it the right answer for everyone. The Shift in the Monitoring Landscape Over the last couple of years, Grafana has consolidated both metrics and log collection into Grafana Alloy. Grafana Agent reached end of life on November 1, 2025, and Promtail followed on March 2, 2026. Neither receives security fixes anymore. The practical choice moving forward: Feature Prometheus Agent Grafana Alloy Metrics ✅ ✅ Logs ❌ ✅ Traces ❌ ✅ Config Prometheus YAML Alloy components Footprint Smaller Larger Learning curve Low Moderate Future direction Metrics agent Unified telemetry The table gives the short answer. The rest of this article explains where those differences actually matter in practice. Prometheus Agent mode. Run the Prometheus binary with the --agent flag and it stops acting as a full Prometheus server. It no longer stores local TSDB blocks, evaluates alerting rules, or serves queries. Instead, it scrapes targets, buffers samples in a write-ahead log, and forwards them upstream via remote_write . It is Prometheus with the storage and query layers removed. Grafana Alloy. A single agent that collects metrics, logs, and traces, processes them in a component pipeline, and pushes each signal to its backend. It embeds many exporters directly, so a line like prometheus.exporter.unix "node_exporter" {} gives you full node_exporter functionality without installing a separate binary. The Case for Prometheus Agent If you only need m

The problem I've been working with Manticore Search for about two years at EricaPRO , building the search layer for two financial data platforms. For the past year, that work has been a Laravel API. Manticore was never the problem. It's fast and it's stable. The problem was the gap between Manticore and Laravel. I had already built a package for this — laravel-manticore-search , a fluent builder over Manticore's HTTP/JSON API. It works, and it's still in use. But it's a client wrapper. Every feature had to be implemented manually. Every new filter or facet meant more custom architecture around the client, and none of the things Laravel gives you for free — models, migrations, pagination, casts — applied to it. Scout doesn't close that gap either. Scout gives you search() . No full query builder, no migrations for your indexes, sync is your problem. That's not a criticism — Scout abstracts over engines with completely different APIs, so it exposes the lowest common denominator. It just wasn't what I needed. What I needed was simple to describe and annoying to not have: something plug and play. Something Laravel way. Point Eloquent at Manticore and use Eloquent. The insight Manticore speaks the MySQL wire protocol. Out of the box, port 9306. You can connect to it with any MySQL client and run SQL. I had been using that port for two years without thinking about what it meant for Laravel. Because here's the thing: all of Eloquent — models, query builder, migrations, pagination, chunking — sits on top of a Connection and a Grammar . The grammar compiles builder calls into SQL for a specific dialect. That's the entire mechanism behind Laravel supporting MySQL, Postgres, SQLite and SQL Server with one codebase. So the real question was never "how do I re-implement Eloquent on top of Manticore's client?" It was "how thin can a Manticore grammar be?" If Manticore accepts MySQL-protocol connections and mostly-MySQL SQL, then a Laravel database driver — a custom connection plu

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.

There’s more to Google’s messaging app than you might realize.

It’s not the upgrade Ring 4 owners have been waiting for, but it’s easily the best smart ring Oura has ever made.

Armed with high-end knives and digital calipers, Germanbreadcutter has entranced thousands of fans, one loaf at a time.

An increasing number of people seem to agree the internet is terrible for children - allegedly addictive, destructive to self-esteem, possibly a portal to predators. Over the past year, several countries have started requiring stringent age verification or outright bans for minors. At the end of June in the US, the House of Representatives passed […]

On this week’s episode of The Big Interview podcast, WIRED’s senior culture editor Manisha Krishnan talks to Gowanus about eschewing Big Tech, going outside, and rejection in the age of dating apps.

AI makes the first 80% of development feel fast, but hides architectural complexity until it's too late. To prevent system instability, engineering leaders must shift from raw throughput to systemic comprehension. By unifying spec-anchored SDD, TDD, and automated fitness functions into a repo-bound "Context Store," teams can ensure AI agents and human reviewers evolve code safely. By Stella Berhe, Stephan Bragner, Vikram Maran, Anand Jayaraman

“On-device AI saves battery” and “cloud AI is more efficient” can both sound plausible. Neither is a measurement. The placement decision crosses at least four different budgets: user wait + network transfer + provider spend + device energy Do not collapse them into one vague “cost” number. Measure each with its own unit and evidence boundary. Start by identifying the actual execution path I reviewed MonkeyCode mobile code at commit c58bcd4 . The task stream opens a server-supported WebSocket. The speech-to-text hook also participates in a server-supported streaming path. That reviewed path is not evidence of on-device model inference. So a fair current study would measure a mobile client using remote task and voice services. An on-device alternative would be a separate prototype with its model, runtime, and packaging declared. Record a measurement envelope The included CSV template begins with these fields: sample_id,sample_kind,placement,device,os,framework,model,network,input_tokens,output_tokens,latency_ms,bytes_up,bytes_down,energy_joules,cost_usd Why so many? device , os , and framework make thermal and runtime results interpretable; model and token counts keep workload size visible; network separates offline, Wi-Fi, and cellular behavior; latency is milliseconds, transfer is bytes, energy is joules, and provider spend is currency; sample_kind prevents synthetic examples from masquerading as device measurements. Battery percentage is too coarse for short runs. It is affected by display, radio, background work, battery health, temperature, and OS estimation. If you cannot collect energy with an appropriate platform profiler or external power measurement, leave energy_joules empty. Use matched user flows Compare the same tasks, not unrelated model demos: Flow Cloud case On-device case Short prompt Same input and output cap Same semantic task and cap Voice turn Same audio fixture Same audio fixture Offline Expected failure or queued action Local completion if supp

Uber Chief Product Officer Sachin Kansal walks TechCrunch through the company's financial-services ambitions, its increasingly complicated relationship with Waymo, its new AV Labs data operation, and how AI is starting to show up in ways riders and drivers will actually notice.

Apple’s revamped Siri is more than a voice assistant; it’s now the backbone of the iPhone user experience. You can try it now through the iOS 27 public beta.

Rendering a big image on iOS is one of those things that looks trivial until your app gets killed by the OS mid-export. CGContext , draw, makeImage() , done — except the moment the output gets large, that innocent-looking pipeline quietly asks for gigabytes of RAM and iOS terminates you. I hit this wall building Mozary , an iOS app that packs 100+ photos into a single giant picture (a photo mosaic). In v1.1.0 I finally killed the "high-resolution export crashes with out-of-memory" bug for good. The fix: stop putting the canvas in RAM at all. Put it in a memory-mapped file and let the OS page it to disk. RAM usage dropped from "4.8 GB, please die" to a few dozen MB, flat, regardless of output size. This post is the walkthrough — with the actual Swift. If you've ever seen Core Graphics blow up on a big image (mosaics, collages, stitched panoramas, high-res rendering — same trap), this is for you. TL;DR A non-compressed bitmap costs 4 bytes/pixel . A 1.2-gigapixel image = ~4.8 GB of RAM just for the canvas. CGContext(data: nil, ...) allocates that in RAM. context.makeImage() then copies it again . Double death. Back the canvas with a memory-mapped file ( mmap ). Writes transparently page out to disk and don't count against your app's memory footprint . Wrap that same mapping in a CGImage via CGDataProvider — zero copy — and stream it straight to a JPEG on disk. Never call makeImage() . Decode source tiles at their draw size , not full size. Because you now spend disk instead of RAM: add a free-space pre-flight check and clean up temp files after a crash. Let's dig in. The problem: "compressed file size" is a lie about memory Mozary lays photos out on a grid. A typical high-res export is a 200 × 267 grid with each tile drawn at 150px : width: 200 × 150 = 30,000 px height: 267 × 150 = 40,050 px That's ~1.2 gigapixels . Here's the part people underestimate: the final JPEG is only a few hundred MB to ~2 GB because JPEG is compressed . But while you're drawing, the canvas i

Siri has been on the Apple Watch since day one, though I'm usually hard-pressed to find people who actually make good use of it. It's kind of just… been there - mostly as a way to set timers when my hands are full. But after playing around with the watchOS 27 developer beta, I get […]

iOS 27 escaped the developer world today with the launch of the first public beta. I've been testing the new operating system since early June, looking for quirks and seeing if it can live up to the hype Apple promised in the keynote. This year's iOS upgrades are what one might call a Snow Leopard […]