今日已更新 264 条资讯 | 累计 23847 条内容
关于我们

标签:#review

找到 220 篇相关文章

开源项目

These camera-free smart glasses made me feel like Tony Stark

Xgimi, the Chinese company known for its all-in-one smart projectors, is expanding its portfolio with a new line of screen-equipped smart glasses that first debuted at CES 2026. Unlike AR glasses from companies like Meta and Snap, Xgimi’s new privacy-focused MemoMind One skip cameras for a lighter and more discreet design that helps hide their […]

2026-06-29 原文 →
AI 资讯

No Agent Grades Its Own Homework

You ask Claude to review your code. It says "looks good, clean, well factored". Of course it does. It wrote that code five minutes ago. You just asked the author to grade his own paper, and he gave himself an A. Having an AI review code works. But not by asking the one who just wrote it. Quality doesn't come from a smarter model, it comes from an architecture where no role checks itself. The self-preference bias This isn't a hunch, it's measured. A model evaluating its own output rates it higher than others' at equal quality: the self-preference bias , documented by Panickssery and co-authors in 2024, and it's causal, not correlational. The model recognizes its own style and prefers it. In practice that means the naive loop "write, then review what you just wrote" is broken by construction. You don't get a review, you get a justification. The agent already decided its code was good the moment it produced it; asking again only confirms. The blind reviewer So the first rule: the reviewer is never the author. In my config, the review agents run in a clean context . They don't see the implementation prompt, they don't know what constraints the author set, they meet the diff like a colleague on Monday morning. And when the author is a known model, the reviewer is from a different family , to break style recognition. One detail matters as much as the rest: the developer's name never enters the reviewer's prompt. No "this was written by a senior", no "review this model's work". The author's identity is exactly the information that triggers the bias. We take it off the table. No finding without a receipt The second trap is the opposite of the first. An AI reviewer, especially in a clean context, tends to over-flag: it invents problems to look useful, it flags "vulnerabilities" that aren't. A review that cries wolf on every line is no better than a complacent one: either way, you stop listening. Hence the receipt rule. Every finding must cite a file:line and pass a check bef

2026-06-28 原文 →
AI 资讯

TMD’s keyless bike lock is a $280 solution to a $60 problem

I've seen lots of so-called "smart" bike locks over the years, but none so far could justify the added cost. A newcomer that got its start securing ATMs for banks is trying to change that. There's nothing wholly unique about the TMD Chain Lock, but the combination of materials, performance, and insurance-friendly ART-2 certification makes […]

2026-06-28 原文 →
AI 资讯

This puzzle game’s simple premise hides surprising depth

What's the Password? has a simple concept: To solve each of the game's more than 100 puzzles, you have to type in the right four-digit password on a number pad. That might sound like a limited constraint. But the simplicity gives solo developer Dan DiIorio, better known as TrampolineTales, lots of room to play with […]

2026-06-27 原文 →
开发者

Oppo’s Bubble selfie screen is crying out for Qi2

The Oppo Bubble is a smart second screen for your phone, one that can be attached and detached at will, connects wirelessly, and serves as either a selfie screen or a wireless camera remote. It's the best version of this idea I've used yet, but also a frustrating reminder that it could be even better […]

2026-06-26 原文 →
开发者

BYOK is my new go-to distraction-free writing tool

I have long been on the hunt for the perfect distraction-free writing setup. The latest contender is BYOK, which stands for Bring Your Own Keyboard. It's a simple $199 black plastic rectangle with a low-resolution LCD screen that lets you edit text and does almost nothing else. I've tried dedicated apps. I've even converted an […]

2026-06-26 原文 →
AI 资讯

I drove the Slate Truck — there’s more to it than EV minimalism

With its new pickup, Slate Auto is making a simple bet: price matters more than almost anything else. The company announced today that the American-made electric truck will start at $24,950, placing it squarely in the mid-$20,000 price range it had originally promised and making it the least expensive pickup truck and EV available today. […]

2026-06-24 原文 →
AI 资讯

Star Fox is the Switch 2’s most impressive visual showcase yet

The biggest Switch 2 exclusives so far have largely been about scale. Mario Kart World introduced a wide open continent to race across, Donkey Kong Bananza let you smash basically everything around you, and Pokopia brought an expansive Minecraft-style creative experience to the Pokémon universe. Star Fox is different. A remake of a Nintendo 64 […]

2026-06-24 原文 →
AI 资讯

I’m not giving up my Steam Deck for MSI’s new Claw

This is not a review of the MSI Claw 8 EX AI Plus, the first gaming handheld available with Intel's new Arc G3 Extreme handheld gaming chip. Now that my colleague Sean Hollister is done reviewing the Steam Machine, I'll let him go deep on the new Claw at some point in the future. This […]

2026-06-23 原文 →