Instant markdown previews in Finder Discussion | Link

TL;DR Short version: no. I dropped a much older GPU ( Quadro P2000, 5GB, Pascal, 2016 ) next to an RTX 3090 (24GB, Ampere) on the same box, ran the same context-length ladder (8K→128K) through Ollama and vLLM on qwen3-coder:30B-A3B , and got zero extra usable context in either engine — and a 74% decode-speed hit for the trouble. Ollama hits the identical Chunk too big wall at ctx=65536 whether the P2000 is there or not. vLLM refuses tensor-parallel across the two cards entirely — not a VRAM problem, a flat compute-capability rejection ( Minimum capability: 75. Current capability: 61. ) that fails in 40 seconds, before any memory profiling. And the one real, measured effect of adding the P2000 to Ollama: decode speed goes from 76 → 19.5 tok/s at ctx=49152 once the P2000 gets pulled in as an actual compute device. Full narrative version — the two-stage collapse, the prompt-cache validation bug caught mid-sweep, the CUDA13-silently-drops-Pascal finding — is on Medium .## The setup ardi (dual Xeon E5-2680 v4, 128GB RAM, openSUSE Leap) has a Quadro P2000 sitting in a second slot next to the RTX 3090 this whole series has run on so far. Same model as phase 1 ( qwen3-coder:30B-A3B ), same box, four legs: {Ollama, vLLM} × {3090 only, 3090+P2000 tandem}, priced through HomeLab Monitor against real GPU power draw. Ollama: same wall, extra tax ctx 3090 only decode tok/s tandem decode tok/s P2000 VRAM (tandem) 8,192 124.3 122.0 6 MB / 0% 24,576 108.2 70.0 62 MB / 0% 32,768 99.4 61.0 62 MB / 0% 49,152 75.7 19.5 3,580 MB / 55% 65,536 fatal: Chunk too big fatal: identical Chunk too big — Two separate costs, not one: decode already falls behind at ctx=24576 while the P2000 is still basically idle (62MB, 0% util) — some scheduling overhead just from having a second visible device. Then the real collapse hits at ctx=49152, when the P2000 actually gets pulled into the compute path (3.58GB, 55% util) and decode craters to 19.5 tok/s . Same context ceiling either way, worse speed the wh

Autonomous agents are starting to trade real money on-chain. Some run their creator's capital, some run other people's, some are wired into vaults and DAO treasuries. The moment money is delegated to a program, two questions matter more than performance: what was it allowed to do, and did it stay inside those limits? Supported chains: Base · Ethereum · Arbitrum · Optimism · Polygon · Hyperliquid · Solana (beta). The chain answers the first question badly and the second not at all. Every trade an on-chain agent makes is public and tamper-evident — you can see exactly what it did. But nowhere on-chain is it recorded what it was authorised to do . The mandate — the rules the agent was supposed to operate under — lives off-chain, unverifiable, usually as a screenshot or a claim. Why this is not a niche problem Copy trading is the same gap at retail scale, and the data is unforgiving. In a 90-day study of 100,236 copy-trading outcomes, 97% of lead traders were profitable on their own PnL — but only 43.6% produced positive PnL for the people copying them. Fewer than half of copiers (48.5%) finished in profit at all. Leaderboards, as that study puts it plainly, show the survivors, not the full picture. The honest response the industry already reaches for is third-party verification: in forex, platforms like Myfxbook exist precisely because a self-reported track record is worth nothing — the data has to come from somewhere the trader can't fake. Crypto has no equivalent that is both agent-native and tamper-evident. That is the hole. Who actually needs this Three groups, concretely: Anyone allocating capital to an agent — a vault depositor, a copy-follower, an allocator sizing a position. They want to see, before they commit, whether an agent keeps to its stated mandate, instead of trusting a screenshot. Anyone running an agent who needs to raise capital or followers — an honest operator has no way today to prove their agent did what it said. A verifiable record is how they

Showcasing Your GitHub Profile: A Guide to Effective Presentation In the world of software development, GitHub profiles serve as a modern-day portfolio, showcasing a developer's skills, projects, and contributions. Whether you are a seasoned developer or just starting out, presenting your GitHub profile effectively can make a significant difference in your professional journey. In this article, we will explore the essential elements of a compelling GitHub profile and provide tips to make your profile stand out in the crowded digital landscape. Understanding the Importance of Your GitHub Profile GitHub is more than just a repository hosting service; it is a platform where developers can collaborate, share their work, and build a professional network. Your GitHub profile is often the first impression a potential employer or collaborator will have of your technical capabilities. A well-crafted profile not only highlights your technical prowess but also your ability to communicate and work within a team. Key Elements of a Compelling GitHub Profile 1. Profile Picture and Bio First impressions matter, even in the digital world. Your profile picture should be professional and clear, giving a face to the name behind the code. Accompanying your picture should be a concise bio that succinctly describes who you are, your interests, and your areas of expertise. This personal touch can make your profile more relatable and memorable. 2. Featured Projects Highlighting a few key projects on your GitHub profile can effectively demonstrate your skills and interests. Choose projects that not only showcase your technical abilities but also reflect your passion and creativity. Provide a clear description of each project, the technologies used, and your specific contributions. This level of detail can help potential employers understand the depth of your knowledge and experience. 3. Consistent Activity An active GitHub profile signals to others that you are engaged in the development com

The issue was not the tools. It was opening five of them before deciding what the log file was for. The log file was already on the screen. A remote Windows workstation had failed a desktop build, and the relevant file was sitting in a local app directory, something like: C:\Users\<user>\AppData\Local\<app>\logs\build.log The remote session was working. The error was visible. The next step seemed small: get the log back to the local laptop, open it in a familiar editor, compare it with the issue notes, and pull out the part that mattered. That should have been a 30-second task. Instead, it turned into five context switches. The first context was the remote session The remote desktop session made sense. The build failed on that machine, the app was installed there, and the log path was easier to find visually than by guessing from memory. So far, nothing was wrong. The file was selected. The timestamp matched the failed run. The log looked useful. It probably had the stack trace, the missing dependency path, or the configuration mismatch that explained the build failure. Then came the small but surprisingly annoying question: How should this file leave the remote machine? That is where the workflow started to wobble. The second context was chat The first instinct in many teams is chat. Drop the file into a message to yourself, a teammate, or the debugging thread. It is fast, already open, and keeps the file near the conversation. For some files, that is the right move. A screenshot, a short error snippet, or a quick “does this look familiar?” artifact belongs naturally in the discussion. But a full log file is not always a chat artifact. If it goes into chat, will anyone know later whether it was the first failing run or the second? Will it be obvious which remote machine produced it? Will the file still be easy to find after the thread moves on? Chat was not wrong. It was just not clearly the right home for this specific file. So the workflow moved on. The third con

Filingrail now ships a first-party MCP server on PyPI: pip install filingrail-mcp . One install, one config block, and Claude Desktop — or Cursor, or Continue, or any MCP-compatible client — can query SEC filings as tools. No glue code. That's worth naming directly. Most SEC-data APIs ship a REST endpoint and stop. You write the agent integration yourself: parse the response, wire up the tool schema, handle auth headers. Filingrail ships the integration as a maintained package with the same update cadence as the underlying REST API. This post covers the setup, what you can ask once it's wired in, and the honest limits. I built both the API and the MCP server — I'll be upfront about that throughout. This post covers a data API that returns SEC-registered financial information. Nothing here is investment advice. Two ways to wire it in Option 1 — pip install filingrail-mcp (recommended) Install the package, add one block to your Claude Desktop config, restart. Filingrail's endpoints appear as tools. No separate service to run, no background daemon. Option 2 — RapidAPI MCP Playground tab (no local install) The Filingrail listing on RapidAPI has an MCP tab that generates a ready-to-paste config block. Same endpoints, same auth, zero install step. Either path gives Claude the same tools. Pick the one that fits your setup. Setup — the pip install path You'll need Python 3.10+ and a RapidAPI key. 1. Subscribe to Filingrail Go to the Filingrail RapidAPI listing and subscribe. Free tier is 50 calls/day, no credit card. Copy your X-RapidAPI-Key from the RapidAPI dashboard. 2. Install the server pip install filingrail-mcp 3. Add Filingrail to your Claude Desktop config On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%\Claude\claude_desktop_config.json { "mcpServers" : { "filingrail" : { "command" : "filingrail-mcp" , "env" : { "RAPIDAPI_KEY" : "your_rapidapi_key_here" } } } } 4. Restart Claude Desktop Filingrail's endpoints appear a

With increased adoption of AI, there is often an argument that code-reviews are now the new bottleneck. And I agree with this completely. Code-Reviews, especially the review you do yourself after AI has written your code, take time. But I would object to the notion that this is a bad thing. What is a bottleneck? A bottleneck is something that slows down the process. It becomes a point where work must get in a line, to pass through a narrow space. With the speed of AI producing code, code reviews become a bottleneck. But is having a bottleneck in the process always a bad thing? The value of slowing down I can only speak from my personal experience of developing software for roughly 7 years now. But in my experience, slowing down is not always bad. On the contrary, it can be very healthy. When you slow down, and take the time to really think about things, you often come up with insights that you would not have if you always rush through things. And these insights can be golden opportunities to change something for the better. Be that a subtle bug discovered, be that a design flaw addressed or something else - the list is long. But as British computer scientist Tony Hoare famously said: "There are two ways of constructing a software design: One way is to make it so simple that there are obviously no deficiencies, and the other way is to make it so complicated that there are no obvious deficiencies." But simplicity is hard "I would have written a shorter letter, but did not have the time." If it was Mark Twain or Blaise Pascal who said it is beside the point. The point is, there is a lot of truth in this quote. A writer of prose I know also confirmed what many senior software engineers know - to make something complex simple and easily comprehensible takes way more time and effort in the form of careful thought than it takes to leave it being complicated and hard to understand. AI is good at writing code quickly, yes. But is it also good at writing code which has high q

I built an LED Strip Tetris game — without writing a single line of code. No keyboard mashing. No debugging at 2 AM. No reading 500 pages of datasheets. Just natural language prompts, an AI agent, and a Tuya T5 AI Core board. Here's the full breakdown of how it works 👇 🧩 What Is LED Strip Tetris? LED Strip Tetris is a DIY hardware game built entirely through natural language prompts using TuyaOpen IDE and Claude Code. It runs on a Tuya T5 AI Core development board with a WS2812 LED strip (72 LEDs) and three color-matched buttons — red, green, and blue. Colored LEDs fall from the top of the strip; players press the matching button to shoot a colored LED upward and eliminate the falling one on contact. The entire game — firmware, game logic, hardware wiring, sound effects, compilation, and flashing — was generated by AI. Zero manual coding. 🔌 The Hardware (Ridiculously Simple) Component Role Tuya T5 AI Core Board Main MCU — runs game logic, drives LED strip and buttons WS2812 LED Strip (72 LEDs) Display — colored LEDs fall and get eliminated 3 Push Buttons (Red / Green / Blue) Input — shoot matching color upward to clear falling LEDs Speaker Sound effects on button press That's it. No custom PCB. No complex wiring harness. Just four components plugged into a dev board. 🤔 Why This Is a Big Deal Here's what building a hardware game normally looks like: Step Traditional Approach Vibe Coding with TuyaOpen IDE Dev environment setup Install toolchain, configure SDK, fight dependencies Copy a workflow link, paste into Claude Code, click confirm Game logic Write C code from scratch, design state machines Describe the game in one sentence, AI generates the code Hardware config Read datasheets, look up GPIO mappings, manually configure Tell AI which pins you're using, it handles the rest Sound effects Write audio decoding code, integrate codecs Give AI the file path, it decodes and compiles Debugging Serial logs, oscilloscope, hours of trial and error AI self-diagnoses compile

We are so excited to announce the winners of the June Solstice Game Jam, our celebration of the...

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Four nuclear reactors hit a big milestone in the US —Casey Crownhart I was really looking forward to July 4, and not just because I love a poolside barbecue. This year…

Comments URL: https://news.ycombinator.com/item?id=48844517 Points: 0 # Comments: 0

Nilekani remains Fundamentum's anchor investor as the firm expands its leadership team and targets AI and fintech startups in India.

Provided you have a library of SNES cartridges, the SN Operator is a seamless plug-and-play system for easy ’90s nostalgia.

Slate's barebones EV trucks lack whimsy, which is why the company has teamed up with Crayola.

A platform is a collaboration system: platform teams depend on application teams, and both need shared standards. Engineers trust a platform through its predictable behavior, not its features. Being an engineer is about problem-solving and being passionate about it. And being an engineer means sharing your passion for problem-solving. By Ben Linders

SpaceX is currently ahead of last year's record-setting pace for Starlink satellite deployments. SpaceX launched 1,589 Starlink satellites into low-Earth orbit in the first half of 2026, according to launch data compiled by Jonathan McDowell's satellite tracker, compared to 1,489 satellites deployed at the same point in 2025. 2025 was already a record year for […]