标签：#Product

Unifies your work into one app with shared memory Discussion | Link

Prime Day isn’t just about cheap TVs. It’s also about cheap stuff to watch on your cheap TV.

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every commit. Star Us to help devs discover the project. Do give it a try and share your feedback for improving the product. An AI model writes a paragraph. It sounds fluent. It looks convincing. But how do you know whether it's actually good? This deceptively simple question has occupied researchers for more than two decades. Long before ChatGPT, machine translation researchers faced exactly the same problem. Human evaluation was expensive, inconsistent, and painfully slow. If every new model required thousands of humans to compare translations, research would crawl. That necessity gave rise to BLEU , one of the most influential evaluation metrics in AI history. Years later, as language models became better at paraphrasing and reasoning, BLEU started to show its age. Researchers responded with learned metrics like BLEURT and COMET , which use neural networks to judge language much more like humans do. Interestingly, this mirrors software engineering itself. We first wrote simple unit tests, then integration tests, and today we increasingly rely on sophisticated observability systems. Evaluation metrics for LLMs have undergone a similar evolution. Let's see why. Before BLEU: The Evaluation Bottleneck Imagine you're building Google Translate in 2001. Every time your team improves the model, someone has to read thousands of translated sentences and score them. Suppose a single sentence pair takes only 20 seconds to judge. Evaluating 50,000 sentences would require nearly 280 human-hours . Now imagine dozens of experiments every week. Evaluation—not training—quickly becomes the bottleneck. Researchers at IBM, led by Kishore Papineni , introduced BLEU (Bilingual Evaluation Understudy) in 2002 to automate this process. Their idea was surprisingly simple: If a machine translation resembles what professional translators write, it's probably good. This became one of the most cited papers

How I built an open-source Slack assistant with persistent semantic memory, powered by any LLM and Mem0's managed memory layer — no vector database required. The problem with Slack bots and memory Most AI Slack bots have the memory of a goldfish. Every conversation starts from scratch. You ask it about your sprint goals, it gives a great answer, then three days later you ask a follow-up and it has no idea what you're talking about. You end up re-explaining context constantly. The commercial solution to this is Claude Tag — a Slack integration that maintains genuine conversational continuity. But it's tied to one provider and not open-source. slacktag-oss is our attempt to replicate that experience: a Slack bot with real, semantic, persistent memory that works with any LLM — including ones running entirely on your laptop. What I built A Python Slack bot with: Socket Mode for local dev (no public URL needed), HTTP-ready for prod LangChain to abstract LLM calls across any OpenAI-compatible endpoint Mem0 managed cloud for semantic memory — no Qdrant, no Pinecone, no infra to run Three memory scopes: per-channel, per-thread, per-DM Built-in !clear and !memory commands A clean, extensible architecture you can fork and build on Architecture Before diving into code, here's the full request lifecycle: ┌─────────────────────────────────────────────────────────────┐ │ Slack │ │ @mention in channel ──┐ │ │ DM to bot ──┼──► Slack Events API │ │ Thread reply ──┘ │ │ └───────────────────────────────────│─────────────────────────┘ │ (Socket Mode / HTTP) ▼ ┌─────────────────────────────────────────────────────────────┐ │ slack-bolt (Python) │ │ bot.py ──► router.py ──► handler.py │ │ │ │ │ ┌───────────────┤ │ │ │ │ │ │ ▼ ▼ │ │ Mem0 Client LangChain │ │ (managed) ChatOpenAI │ └────────────────────────────────────────────────────────────-┘ │ ▼ ┌───────────────────────┐ │ Mem0 Managed Cloud │ │ Vector Embeddings │ │ Entity Extraction │ │ Deduplication │ └───────────────────────┘ The ke

J'utilise la dictée vocale tous les jours depuis six mois. Pas pour taper moins vite. Pour penser plus vite quand je vibe-code avec Claude Code et Cursor. Pis j'ai fini par construire mon propre outil parce que les outils existants me tapaient sur les nerfs d'une façon très précise. Le problème réel Quand tu travailles en tech au Québec, tes phrases ressemblent à ça : "OK fa que je fais un useState pour le component pis je passe le handler en props" Ça, c'est une phrase normale. Personne en tech QC ne parle autrement. Pas parce qu'on est négligents avec la langue. Parce que le vocabulaire technique vient de l'anglais et qu'on le soude naturellement au français au fil de la pensée. Ça s'appelle le code-switching. Et c'est là que la plupart des outils de dictée craquent. Ce que les outils mainstream font mal Dragon NaturallySpeaking Dragon, c'est le vieux standard. Médical, juridique, corporate. Ça coûte environ 500$ en une shot. C'est lourd à installer et à entraîner. Et sa gestion du français québécois avec des termes tech intercalés... c'est en gros zéro. "useState" devient "usé état". "Fa que" devient "faque" parfois, "fake" d'autres fois. C'est aléatoire. T'as intérêt à corriger après chaque phrase. Wispr Flow Wispr Flow est plus moderne. UX propre, cross-platform, et leur gestion du français s'est améliorée. Leur plan Pro coûte 15$/mois, soit environ 144$/an. Mais il y a un problème structurel que leur propre doc admet : la détection de langue se fait par session, pas par mot. Autrement dit : Wispr détecte la langue une fois au début de la session. Si tu commences en français, il reste en mode français jusqu'à la fin. Les mots anglais qui arrivent dans la phrase, il tente de les translittérer en français. "Handler" peut devenir "andler" ou "ender", "props" survit parfois, parfois pas. C'est variable. Pour une phrase de temps en temps avec un mot anglais, ça passe. Pour un vibe-coder québécois qui switch constamment dans la même phrase, ça ne passe pas. Pourquoi

Bose headphones are already one of our favorites for comfort, sound, and noise canceling. Now they’re cheaper.

Apple has warned about MacBook prices rising, making these Prime Day deals even more worthwhile to consider.

It wouldn't be Amazon Prime Day without some beauty deals. Here's a roundup of all our favorites.

These are the best last-minute Prime Day discounts on handheld fans, from $10 budget buys to Shark’s high-tech ChillPill.

This is just an opinion of what I experience and am witnessing, but looking at how LLMs scale feels like I've seen it before: with CPUs trying to outrun Moore's Law and break the rules of physics. Heat, power leakage, and diminishing returns made it increasingly expensive to squeeze out even small gains in clock speed. The GHz race shifted because it had to. For LLMs, more compute, more data, more parameters, and everything just keeps getting better? That curve seems to hit a ceiling and innovation needs to succeed the scaling race now. History does not repeat itself, but it rhymes. What learnings can we make from history to "predict" a potential future? History In the early 2000s, CPUs ran into a wall, a very physical one ^^ So makers adapted. Instead of crunching every single watt out of a single core, multi-cores became common. Athlon 64 x2, Pentium D, PS3 with its heavy Cell approach. From linear to parallel. From sequential to multi-threaded (and funny race conditions ;). Talks of distributed systems, SIMD/MIMD and new benchmarking spawned into what we have today. We still use CPUs, but differently. We still have Memory, but think about Cache, RAM, GPU or Unified. Same same, but different. Innovation because of limitation. Present I feel something similar is about to happen to gen AI. Yes, there are improvements in different areas, some in scaling, some optimisation, some performance, but the slope is becoming slippery. The last 12 months went from "Opus 4.5 is the pinnacle" to "What the hell is wrong with Claude?". The perfect (business) storm of scaling execution! But the low-hanging fruits have been eaten and the crops don't grow as fast anymore. Costs rise quickly, latency becomes a constraint, and even large context windows feel more like extensions than breakthroughs. What remains is more incremental, more expensive, and more complex. You could argue the whole venture of "agents" is the same multi-core experience repeating itself. A different kind of orch

I have a confession. Somewhere around day nine of this experiment, I almost quit and went back to my old setup. Not because ChatGPT was bad. Because I was bad at using it. I kept typing half-questions the way I'd type into Google, hitting enter, and getting answers that were technically correct and completely useless. It took me about a week to realize the problem wasn't the tool. It was twelve years of muscle memory. This post is the long version of what happened when I tried to go a full month without my usual stack of developer crutches — Google, Stack Overflow, Regex101, JSONLint, a SQL formatter site, a commit message generator, a pile of bookmarked Docker cheat sheets, and a few other tabs I didn't even realize I kept open until they were gone — and replaced all of it with a single ChatGPT window. I work as a backend-leaning full stack engineer at a small e-commerce company. Python and Django on the server, a chunk of Node for a couple of internal services, Postgres, Docker, and an AWS setup that I inherited rather than designed. Nothing exotic. Which is actually why I think this experiment is useful — most of you reading this aren't working on some bleeding-edge ML pipeline either. You're maintaining stuff, fixing stuff, shipping features under deadlines that someone in another department picked without asking you. So here's what happened. All of it. The good parts, the embarrassing parts, and the parts where I quietly reopened Stack Overflow in an incognito tab because I didn't want my browser history to judge me. TL;DR I tried to replace 12 daily developer tools with ChatGPT for 30 days straight, tracking what worked and what didn't. Google search volume dropped by roughly 70%, but it never hit zero — and I don't think it should. Stack Overflow was the hardest habit to break, and also the one I missed least once I'd broken it. The small utility sites (Regex101, JSONLint, SQL formatters) were the easiest wins. ChatGPT replaced almost all of them outright. Do

Do you crave speedy, reliable Wi-Fi throughout your home? Snag one of these Prime Day router or mesh deals.

I've compiled a list of the best fitness tech deals this Amazon Prime Day, including smartwatches, walking pads, and recovery gear. You can thank me later.

After testing each of the MacBooks myself, here's my honest advice on which is right for you.

Kids love 3D printers almost as much as K-Pop Demon Hunters. Just give in and get one.

OpenAI previews GPT-5.6 Sol, a next-generation model with stronger capabilities in coding, science, and cybersecurity, paired with its most advanced safety stack.

Use it with Claude, ChatGPT and more! Discussion | Link

When I first started using Cursor AI , I thought it was just an AI-powered code editor. After spending more time with it, I realized it's much more than that. Cursor isn't just about generating code—it's a development assistant that can understand your project, automate repetitive tasks, connect with external tools, and help you build software much faster. If you're new to Cursor, this guide will explain the most important concepts in simple language with real-world examples. 1. What are Rules? Think of Rules as permanent instructions for Cursor. Instead of telling the AI the same things every time, you define them once and Cursor follows them throughout your project. Example Instead of writing this every time: Use TypeScript Use Tailwind CSS Create reusable components Write clean code You can create a rule like: Always use TypeScript. Always use Tailwind CSS. Never use inline CSS. Create reusable components. Write meaningful comments. Now every prompt automatically follows these instructions. Real-world example Imagine you're working in a company where every developer follows coding standards. Rules are those standards—but for your AI assistant. Benefits Consistent code Less repetitive prompting Faster development Better code quality 2. What are Skills? Skills are reusable instructions for specific types of work. Instead of explaining how to build an API every time, you create one reusable skill. Example: Create Express APIs using MVC architecture. Validate all inputs. Handle errors properly. Use async/await. Now whenever you ask Cursor to create an API, it follows that workflow. Real-world example A plumber has plumbing skills. An electrician has electrical skills. Similarly, Cursor can have reusable development skills. Benefits Reusable workflows Consistent architecture Faster feature development 3. What are Hooks? Hooks are automatic actions triggered by an event. For example: You save a file. ↓ Cursor automatically runs: Formatter Linter Tests You don't have to

Don't pay full price—snag one of these tasty Prime Day tech deals on some of our favorite WIRED-tested gadgets.

A fast, beautiful, and native FTP/SFTP client for macOS Discussion | Link