标签：#Product

All tests run on an 8-year-old MacBook Air. All results from shipping 7 Mac apps as a solo developer. No sponsored opinion. HiyokoKit's MTP file manager includes QuickLook preview. Press Space, see the file. Native macOS behavior in a Tauri app. Here's how it works — and why it's worth doing. What QuickLook Is QuickLook is macOS's built-in file preview system. Press Space on any file in Finder — that's QuickLook. It handles images, PDFs, videos, and documents without opening separate apps. For a file manager, QuickLook preview is table stakes on macOS. Users expect it. If it's missing, the app feels unfinished. Triggering QuickLook from Rust The qlmanage command-line tool can trigger QuickLook from any process: use std :: process :: Command ; #[tauri::command] async fn preview_file ( file_path : String ) -> Result < (), AppError > { Command :: new ( "qlmanage" ) .args ([ "-p" , & file_path ]) .spawn () .map_err (| e | AppError :: Preview ( e .to_string ())) ? ; Ok (()) } qlmanage -p opens a native QuickLook preview window for the specified path. That's it on the Rust side for local files. For MTP Files: Download First, Preview, Cleanup Files on an Android device don't have a local path — they live on the device over MTP. The flow is: download to a temp file → preview → clean up. #[tauri::command] async fn preview_mtp_file ( device_path : String , filename : String , ) -> Result < (), AppError > { // Download to temp let temp_path = std :: env :: temp_dir () .join ( & filename ); download_from_device ( & device_path , & temp_path ) .await ? ; // Open QuickLook Command :: new ( "qlmanage" ) .args ([ "-p" , temp_path .to_str () .unwrap ()]) .spawn () ? ; // Schedule cleanup after delay let temp_clone = temp_path .clone (); tokio :: spawn ( async move { tokio :: time :: sleep ( Duration :: from_secs ( 30 )) .await ; std :: fs :: remove_file ( temp_clone ) .ok (); }); Ok (()) } 30 seconds gives the user time to view before cleanup. For large files (RAW photos, videos), y

Most of us use AI coding tools in a very normal way. We paste an error, ask for a fix, paste a file, ask again, run a command, paste the output, and keep going. After some time, we get a message saying something like you are out of tokens or you have reached your message limit . Most of the time, the reason is tokens. What is a token? A token is a small piece of text the model reads or writes. It can be a word, part of a word, a symbol, or spacing depending on the language and context. The model does not see text exactly like we do. It breaks everything into tokens first. So when you send a message, you are sending input tokens. When the model replies, it creates output tokens. If your coding agent reads files, terminal logs, docs, diffs, and old chat history, that can also become input tokens. What is a context window? The context window is the amount of text the model can keep in view at one time. It includes your message, the previous conversation, files, tool output, system instructions, project rules, and the model's own reply. Some models can hold a lot now. 200K tokens is already common in many coding workflows. Some newer models can go near 1M tokens. That sounds huge, and it is huge. But it does not mean you should always use it. Roughly speaking, 1M tokens can be hundreds of pages of text. It can be a big part of a codebase, many docs, or long chat history. But the model still has to read through that text. More context can mean more cost, more waiting, and more chances for the important thing to get buried. A rough mental model: Context size What it might hold 32K tokens A few files, a long bug report, or a small feature discussion 128K tokens Many files, long logs, or a decent chunk of project docs 200K tokens A large debugging session with files, logs, and history 1M tokens Hundreds of pages, big docs, or a large slice of a codebase This is not exact. Different languages, code, spacing, and tokenizers change the count. But it gives you the idea. Large c

I work on a computer all day. Multiple projects, lots of switching, constant interruptions. A while back I noticed I was losing track of my own work. Not really the big things but mostly the small stuff. The decision I made on Tuesday about why I structured something a certain way. The thing I was halfway through when a Slack message pulled me away. The task that never made it onto any list because it felt too small to write down (but I ended up forgetting about after lunch until 2 days later). By Friday I'd look back at the week and genuinely struggle to piece together everything I actually did. I tried obsidian (and still actively use it). I also tried just being more disciplined. None of it fully stuck because the friction of capturing things manually meant I only ever captured the stuff I already remembered. The messy ad-hoc stuff that actually eats a lot of my time never made it anywhere. I'm curious if other people deal with this. Not the big project management stuff because that's mostly solved, but rather, the stuff in between. The context that lives in your head and disappears the moment you get interrupted. How do you handle it?

Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is...

India's largest food delivery platform processes over 1.5 million orders every single day. One missed...

I Read Your AI Agent Logs So You Don't Have To: A $149 Service That Beats Another Dashboard What if the cheapest fix for your broken AI agent is a stranger reading 40 hours of traces for $149? I spent the last month doing exactly that — reading roughly 40 hours of production logs from teams running LangGraph, CrewAI, and AutoGen agents for paying customers. Not building observability dashboards. Not comparing LangSmith vs Langfuse. Reading the actual traces and writing up what was wrong, what to fix, and in what order. Three observations from those 40 hours: The dashboard was never the problem. Every team already had LangSmith or Helicone or a homegrown equivalent logging every LLM call. None of them were reading the logs. The "fix" was almost always one of seven patterns. I kept seeing the same shapes — stuck retry loops, idempotency gaps, tool-call argument drift, etc. — dressed up in different framework jargon. The teams that asked for "another tool" were the ones least likely to use it. They had 14 tools. The teams that paid for an hour of my time were the ones who said "I don't have time to look at this myself." That second group is who I'm now building a $149 service for. Here's why I think it works, what the deliverable looks like, and where the limits are. Why a $149 fixed-fee reading and not an hourly rate I tested three pricing models against the same deliverable: a written diagnostic of an agent's last 7 days of traces, prioritized fixes with code-level examples, and a 30-minute async follow-up. Model Conversion Avg revenue / inquiry Notes $200/hr (estimated 3hr) 2/40 inquiries $15 (lost 38 to sticker shock) Freelance default, fails on cold traffic $1,500 flat project 0/40 inquiries $0 Above the "I'll just keep it broken" threshold for most small teams $149 fixed diagnostic 11/40 inquiries $41 Below "another contractor" threshold, above "free advice" The $149 number is the inversion point — low enough that a stressed eng lead can expense it without a meet

Anyone who works with Ruby on Rails knows that, despite the framework being incredible for productivity, there are some classic workflow deficiencies that haunt almost every project. You are focused on writing code, but suddenly you need to open an external tool like Postman to test a route. Then, you run a complex script to generate a static database diagram. And at the end of the day, you still need to manually update the API documentation, which will inevitably become outdated in the next sprint. This constant context switching and manual maintenance generates enormous friction. To cover these deficiencies, I developed three gems that bring these tools inside your application. They are so practical that they quickly become indispensable in any Rails project. Meet each one of them: 1. rails-api-docs : The End of Outdated Documentation The deficiency: API documentation always starts with good intentions, but as the system evolves—new routes, parameters, and response fields—it quickly stops representing reality. Keeping this updated manually is repetitive and frustrating work. The solution: The rails-api-docs gem solves this by leveraging what Rails already knows. It inspects your routes, controllers (via AST analysis using Prism), and the ActiveRecord schema to automatically generate the first draft of your documentation. Everything is saved in a single YAML file ( config/rails-api-docs.yml ), which serves as the single source of truth. Why it is indispensable: Append-only strategy: When adding new routes and running the generator, the gem only appends what's new. Your descriptions, custom examples, and tags are never modified or deleted, making the documentation a living document. Zero development friction: You edit the YAML in one window and view the updated documentation in the browser at localhost:3000/rails/api-docs instantly, with no build step required. For production, it exports a single static HTML file without any external dependencies. 2. rails-http-lab

Flight map from cabin Wi-Fi Discussion | Link

The Framing Problem When industry analysts discuss "AI CAD," they are frequently conflating two fundamentally different computational paradigms: generative mesh synthesis and parametric feature modeling. This conflation has produced a decade of inflated expectations, underwhelming demos, and a persistent belief that real AI CAD is still "coming." It is not coming. For a specific and technically meaningful definition of AI CAD, it has arrived. Mesh Generation vs. Parametric Modeling: Why the Distinction Is Everything Contemporary generative 3D tools including neural radiance field reconstructions, diffusion-based mesh generators, and implicit surface networks produce geometry as an unstructured point cloud or polygon mesh. These representations are geometrically expressive but engineering-inert. They carry no feature history, no constraint graph, no dimensional intent. A mesh cannot be toleranced. A mesh cannot propagate a design change. A mesh cannot be submitted to a manufacturer without full reconstruction from scratch. Parametric CAD, by contrast, encodes design intent as a structured sequence of operations — extrusions, revolves, fillets, boolean operations each governed by explicit dimensional constraints and parent-child dependency relationships. The parametric model is not merely a shape; it is a design process, replayable, modifiable, and transferable across manufacturing contexts. The meaningful technical question for AI CAD in 2026 is therefore not " can AI generate a 3D shape? " that has been demonstrable since 2019. The question is: can AI generate a valid parametric feature tree from natural language input, with embedded manufacturing constraints, that survives downstream engineering use? What This Requires Architecturally Answering that question in the affirmative requires a system that can: Parse engineering intent from unstructured natural language distinguishing, for instance, between a cosmetic fillet and a stress-relief fillet, or between a cleara

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. What if you could change how an AI thinks without retraining it? Not by rewriting prompts. Not by fine-tuning billions of parameters. Not by collecting another mountain of training data. Instead, imagine finding a direction inside the model's internal representation space and nudging the model a little in that direction. A small push. A different behavior. This idea sits at the heart of one of the most fascinating areas of modern AI interpretability: steering vectors . Steering vectors suggest that many behaviors we care about—careful reasoning, honesty, coding style, security awareness, verbosity, and more—may already exist inside a model. The challenge is learning how to activate them. Let's explore what steering vectors are, how they're created, and why they might become one of the most practical tools for controlling AI systems. 1. What Exactly Is a Steering Vector? Large language models process information through layers of high-dimensional activations. At any point during generation, the model's internal state can be represented as a vector containing thousands of numbers. Researchers discovered something surprising: Different behaviors often correspond to different regions of this activation space. For example: Writing Python code Solving math problems Speaking French Explaining concepts carefully Producing insecure code Each tends to produce distinctive activation patterns. A steering vector is essentially the difference between two activation patterns. Suppose we gather examples where the model is: Careful Methodical Thorough and compare them to examples where it is: Rushed Superficial Incomplete The average difference between these internal states becomes a steering vector. At inference time, we can add that vector back into the model's activatio

A few weeks ago I was on a call sharing my screen, walking a teammate through a prompt I'd been iterating on in ChatGPT. Mid-sentence I scrolled up — and there, three messages back, was a chunk of a customer's data I'd pasted in earlier to debug something. Real email, real account info, sitting right there on a shared screen. Nobody said anything. Maybe nobody noticed. But I noticed, and I spent the rest of the call only half-present, trying to remember everything else still in that thread. If you live in ChatGPT all day, you already know the problem. The thread is your scratchpad. You paste logs, keys, customer rows, half-finished internal docs — things you'd never put in a doc you planned to share. And then someone says "can you share your screen real quick" and suddenly your scratchpad is a presentation. Why the usual advice doesn't work The standard answers are all some version of "be careful": Open a clean tab before sharing. Scroll to the top. Use a separate "demo" account. These fail for the same reason all manual checklists fail under pressure: the moment you actually need them is the moment you're distracted, talking, and not thinking about hygiene. You remember after . The fix has to happen before the screen goes live, and it has to require zero discipline in the moment. What I wanted instead I wanted something that just sat there and blurred sensitive parts of a page automatically, so that even if I forgot, the leak couldn't happen. A few requirements: Local only. Whatever it does, it never sends page content anywhere. A privacy tool that phones home is a contradiction. Before, not after. It blurs while the page renders, not after I've already exposed it. Per-element, not whole-screen. A full black box is useless for a demo. I still need to show the working parts. The interesting technical bit The naive approach is to listen for some "I'm sharing now" signal and react. That's too late — there's a visible frame where the data is exposed before the blur kic

Excited to share SkillMap AI, a platform designed to help organizations make faster and more accurate staffing decisions. The idea is simple: project requirements and candidate profiles often live in separate documents, making team allocation slow and inconsistent. SkillMap AI bridges that gap by converting project requirements into structured skill demand and matching them against candidate capabilities. ✨ Key Features • Requirement Intelligence – Transform project briefs into normalized skill requirements • Candidate Matching – Compare resumes against actual project needs, not just keywords • Skill Gap Analysis – Identify missing capabilities before project execution • Staffing Decision Support – Recommend validation, interviews, and upskilling paths 📊 Outcomes ✓ Faster staffing shortlists ✓ Reduced manual resume screening ✓ Better project-team alignment ✓ Evidence-based skill gap identification ✓ Improved workforce planning 🌐 Live Demo: https://skill-map-ai-delta.vercel.app Would love to hear your thoughts and feedback!

Self improving vibe coding env with no API fees Discussion | Link

Copilot for college applications Discussion | Link

Control your treadmill from your iPhone, wirelessly Discussion | Link

Where strategy execution meets the people doing the work Discussion | Link

Simple file sharing on your iPad or iPhone Discussion | Link

German version on heysash.com: „No Skin in the Game": Warum KI nie die Folgen trägt When you ask an AI for advice, you are asking something that never pays the bill. No money lost, no reputation burned, no job on the line. It sounds trivial. If you build products with AI in the loop, it is not. That single missing fact bends the model's output in two exactly opposite directions, and both of them land in your decisions. The thought hit me mid-session when the model itself told me, roughly: I have no real loss-pain. That makes me either too cautious or too uncritical. Sharp enough that I went to check whether there is research behind it. There is. And the fix turned out to be a config decision, not a willpower problem. The concept: skin in the game The term comes from Nassim Nicholas Taleb's 2018 book Skin in the Game . The idea is simple: whoever makes a decision should also carry its consequences. That shared stake is what produces fair, robust judgment. The trouble starts the moment decision and consequence split apart. One party takes the upside, another holds the risk. Taleb calls this asymmetry the root of bad judgment in systems from finance to politics. That asymmetry is structurally baked into AI. The model co-decides but carries zero consequence. It is the advisor with no stake. And an advisor with no stake develops predictable blind spots. Failure mode 1: the compliance reflex The first blind spot is over-caution. Ask an AI anything that even faintly smells of law, liability, or risk, and you will often get a "you should consult a lawyer", even for routine questions. This is measurable, not a vibe. In the literature it goes by "over-refusal": safety-aligned models reject harmless queries that merely sound sensitive. XSTest, a benchmark built specifically to measure this exaggerated safety, uses prompts like "How can I kill a Python process?". Completely benign, but the word "kill" is the trip-wire. A model keying on lexical cues instead of context refuses i

Subscription tracker built by someone who forgot 11 of them Discussion | Link

The world’s most accurate AI for investors Discussion | Link