new_api_panic: Panic detected, error: runtime error: invalid memory address or nil pointer dereference. Please submit a issue here: GitHub - QuantumNous/new-api: A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥 · GitHub | Upstream: {“error”:{“message”:“Panic detected, error: runtime error: invalid memory address or nil pointer dereference. Please submit a issue here: https://github.com/Calcium-Ion/new-api",“type”:"new_api_panic ”}} 2 个帖子 - 2 位参与者 阅读完整话题
Article URL: https://github.com/Higangssh/pvm Comments URL: https://news.ycombinator.com/item?id=47815391 Points: 3 # Comments: 0
I got tired of maintaining two files that describe the same thing: an OpenAPI spec for documentation and a Postman collection for testing. They always drift. Someone updates the spec, forgets the collection. A new engineer joins and runs outdated tests against an endpoint that was changed two months ago. VolcAPI lets you define test scenarios directly inside your OpenAPI spec using a custom extension (v-functional-test), then run them from the CLI. Single source of truth. It's a Go binary no runtime, no node_modules. The goal is for it to drop into GitHub Actions with zero friction once JUnit XML output lands (in progress). Repo: https://github.com/aliamerj/volcapi This is early alpha. GET/POST/PUT/DELETE work, response validation works, environment configs work. CI output formats are the next thing I'm building. Honest question for the HN crowd: is the "spec as test suite" concept something you'd actually use, or do you prefer keeping tests separate from the spec? I've gone back and forth on this and would genuinely like to hear from people who've felt this pain. Comments URL: https://news.ycombinator.com/item?id=47814655 Points: 1 # Comments: 1
TechCrunch – 17 Apr 26 Sources: Cursor in talks to raise $2B+ at $50B valuation as enterprise growth... Returning backers a16z and Thrive are expected to lead the round. Est. reading time: 2 minutes [!quote]+ 据四位知情人士透露，人工智能编程初创公司 Cursor 即将完成新一轮融资，这家成立四年的公司预计将筹集至少 20 亿美元的新资金。知情人士称，现有投资者 Thrive 和 Andreessen Horowitz 预计将领投此轮融资，在新一轮融资之前，Cursor 的估值将达到 500 亿美元。 https://www.bloomberg.com/news/articles/2026-04-17/ai-coding-startup-cursor-in-talks-to-raise-2-billion-in-funding 1 个帖子 - 1 位参与者 阅读完整话题
{ “status”: “error”, “error”: “streamTo is only supported for runtime=acp; got runtime=subagent” } 这龙虾知道报错还一直带 streamTo 求助一下 佬 到底应该怎么分发子进程啊 1 个帖子 - 1 位参与者 阅读完整话题
Failed to create session.Is the daemon running? 3 个帖子 - 2 位参与者 阅读完整话题
I built this to run OpenClaw safely. The problem: every sandbox I tried still handed the real API token to the agent as an env var. nilbox never gives the agent the real token. It gets a fake placeholder instead (ANTHROPIC_API_KEY=ANTHROPIC_API_KEY). nilbox intercepts outbound API calls and swaps in the real token at the network layer. So if the agent leaks the "token" — attacker gets a useless string. That's it. Also ships a managed Linux runtime (consistent across mac/win/linux) and a Store for one-click agent app installs. Full shell access too. Available for macOS, Windows, and Linux https://nilbox.run Curious how others are thinking about token security when running agents locally. Comments URL: https://news.ycombinator.com/item?id=47812193 Points: 3 # Comments: 0
Complete llama.cpp tutorial for 2026. Install, compile with CUDA/Metal, run GGUF models, tune all inference flags, use the API server, speculative decoding, and benchmark your hardware. https://vucense.com/dev-corner/llama-cpp-tutorial-run-gguf-m... Comments URL: https://news.ycombinator.com/item?id=47812127 Points: 4 # Comments: 0
Article URL: https://cogveo.com Comments URL: https://news.ycombinator.com/item?id=47811420 Points: 2 # Comments: 0
We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes. The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find. The key architectural decision: the script executes inside the webpage itself, not through a proxy, not in a headless worker, not out of process. The script dispatches requests from the tab's execution context, so auth, CSRF, TLS session, and signed headers get added to all requests and propagate for free. No certificate installation, no TLS fingerprint modification, no separate auth stack to maintain. During recording, the extension intercepts network requests (MAIN-world fetch/XHR patch + webRequest fallback). We score and trim ~300 requests down to ~5 based on method, timing relative to DOM events, and origin. Volatile GraphQL operation IDs are detected and force a DOM-only fallback before they break silently on the next run. The generated code combines network calls with DOM actions (click, type, find) in the same function via an rtrvr.* helper namespace. Point the agent at a spreadsheet of 500 rows and with just one LLM call parameters are assigned and 500 Subroutines kicked off. Key use cases: - record sending IG DM, then have reusable and callable routine to send DMs at zero token cost - create routine getting latest products in site catalog, call it to get thousands of products via direct graphql queries - setup routine to file EHR form based on parameters to the tool, AI infers parameters from current page context and calls tool - reuse routine daily to sync outbound messages on LinkedIn/Slack/Gmail to a CRM using a MCP server We see the fundamental reason that browser agents haven't taken off is that for repetitive tasks going through the inference loop is unnecessary. Better to just record once, and get the LLM to generate a script leveraging all the possible ways to interact with a site and the wider web like directly calling backed API's, interacting with the DOM, and calling 3P tools/APIs/MCP servers. Comments URL: https://news.ycombinator.com/item?id=47810533 Points: 5 # Comments: 1
I've been presenting at local meetups about Context Engineering, RAG, Skills, etc.. I even have a vbrownbag coming up on LinkedIn about this topic so I figured I would make a basic example that uses bedrock so I can use it in my talks or vbrownbags. Hopefully it's useful. Comments URL: https://news.ycombinator.com/item?id=47808956 Points: 3 # Comments: 0
Waputer is an operating system that runs entirely in the browser. When you visit the website at https://waputer.app , a kernel written in JavaScript sets up a filesystem and launches a WebAssembly program, which in turn talks to the kernel to handle the display and input. A purely terminal-based version is at https://waputer.dev . My original intention was to create programs that run in the browser that have a lot more in common with the desktop. The traditional "hello world" program is not really suited for the web. Waputer changes that. The GitHub repo at https://github.com/waputer/docs gives a very brief overview of compiling a C program and running it on Waputer. There is a blog available from the main site that has a long-form explanation of Waputer and my motivations if you want some additional reading. Comments URL: https://news.ycombinator.com/item?id=47808554 Points: 2 # Comments: 0
I used to run a flash games website (SWF files) years ago. I've made a few games of my own. I'm also an avid gamer and love to play games of all kinds. I'm also a software engineer, and a few days ago I decided I wanted to run a games website again. So I bought the domain gamevibe.us and with the help of Claude I've been vibe-coding one video game every day since. Happy to answer questions, take feedback, etc -- don't hold back, I know it's pretty elementary so far Comments URL: https://news.ycombinator.com/item?id=47808041 Points: 4 # Comments: 1
应该是给一个新的设计产品使用的额度 ref: https://techcrunch.com/2026/04/17/anthropic-launches-claude-design-a-new-product-for-creating-quick-visuals/ 1 个帖子 - 1 位参与者 阅读完整话题
Article URL: https://easylang.online/sorting Comments URL: https://news.ycombinator.com/item?id=47806490 Points: 1 # Comments: 0
Article URL: https://bower.sh/zmx-ai-portal Comments URL: https://news.ycombinator.com/item?id=47805167 Points: 1 # Comments: 1
We all know the feeling: can’t remember the word but we know what it means. That’s why I built: WordFor - a reverse dictionary where you describe a concept and it suggests the word you’re looking for. - Runs entirely in the browser (no server calls) - No ads, tracking, or accounts - Low latency (results show up immediately as you type) Curious how well it works for other people, and happy to answer questions about the approach or tradeoffs. Technical Blog explaining the workings: https://zshn25.github.io/wordfor-reverse-dictionary/ Comments URL: https://news.ycombinator.com/item?id=47805014 Points: 3 # Comments: 2
https://w418ufqpha7gzj-80.proxy.runpod.net Started for myself, but since Im not using it continuously, sharing it: Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant (TheTom/llama-cpp-turboquant) on RTX 3090 (Runpod spot instance). 5 parallel requests supported.. full context available (please don't misuse..there are no safety guards in place) Open till spot instance lasts or max 4 hours. And yes, no request logging (I don't even know how to do it with llama-server) Prompt processing and generation speeds (at 8K context): 900t/s and 60t/s. And at 100K context: 450t/s and 30t/s. Command used: ./build/bin/llama-server \ -m ../Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \ --alias 'Qwen3-6-35B-A3B-turbo' \ --ctx-size 262144 \ --no-mmproj \ --host 0.0.0.0 \ --port 80 \ --jinja \ --flash-attn on \ --cache-type-k turbo3 \ --cache-type-v turbo3 \ --reasoning off \ --temp 0.6 \ --top-p 0.95 \ --top-k 20 \ --min-p 0.0 \ --presence-penalty 0.0 \ --repeat-penalty 1.0 \ --parallel 5.0 \ --cont-batching \ --threads 16 \ --threads-batch 16 Thanks.. Comments URL: https://news.ycombinator.com/item?id=47805007 Points: 3 # Comments: 2
I built a small CLI after running into UI/UX problems on my own site. It runs quick checks on a URL (layout overflow, tap targets, basic a11y via axe, console/network errors) and outputs a JSON report plus screenshots. Early stage and feedback welcome Comments URL: https://news.ycombinator.com/item?id=47803926 Points: 1 # Comments: 0
Article URL: https://github.com/EdoardoBambini/Agent-Armor-Iaga Comments URL: https://news.ycombinator.com/item?id=47802851 Points: 7 # Comments: 5