XXXX

Show HN: Sourcebot – Self-hosted Perplexity for your codebase 18 by bshzzle | 1 comments Hi HN, We’re Brendan and Michael, the creators of Sourcebot ( https://www.sourcebot.dev/ ), a self-hosted code understanding tool for large codebases. We originally launched on HN 9 months ago with code search ( https://news.ycombinator.com/item?id=41711032 ), and we’re excited to share our newest feature: Ask Sourcebot. Ask Sourcebot is an agentic search tool that lets you ask complex questions about your entire codebase in natural language, and returns a structured response with inline citations back to your code. Some types of questions you might ask: - “How does authentication work in this codebase? What library is being used? What providers can a user log in with?” ( https://demo.sourcebot.dev/~/chat/cmdpjkrbw000bnn7s8of2dm11 ) - “When should I use channels vs. mutexes in go? Find real usages of both and include them in your answer” ( https://demo.sourcebot.dev/~/chat/cmdpiuqhu000bpg7s9hp...

Emacs: The macOS Bug 29 by xlii | 7 comments on Hacker News.

How the Brain Increases Blood Flow on Demand 6 by gmays | 0 comments on Hacker News.

The Secret Stanford Program No One's Heard About 7 by curioustock | 3 comments on Hacker News.

Claude Code weekly rate limits 57 by thebestmoshe | 113 comments Hi there, Next month, we're introducing new weekly rate limits for Claude subscribers, affecting less than 5% of users based on current usage patterns. Claude Code, especially as part of our subscription bundle, has seen unprecedented growth. At the same time, we’ve identified policy violations like account sharing and reselling access—and advanced usage patterns like running Claude 24/7 in the background—that are impacting system capacity for all. Our new rate limits address these issues and provide a more equitable experience for all users. What’s changing: Starting August 28, we're introducing weekly usage limits alongside our existing 5-hour limits: Current: Usage limit that resets every 5 hours (no change) New: Overall weekly limit that resets every 7 days New: Claude Opus 4 weekly limit that resets every 7 days As we learn more about how developers use Claude Code, we may adjust usage limits to better serve...

Britain's spies-for-hire are running wild 22 by bingden | 0 comments on Hacker News.

Instrumenting Next.js with runtime secret injection 6 by nimishk | 7 comments on Hacker News.

The Sail instruction-set semantics specification language 3 by weinzierl | 0 comments on Hacker News.

Svalbard winter warming is reaching melting point 23 by toomuchtodo | 2 comments on Hacker News.

Google in 1999: Search Engines Escape the Portal Matrix 3 by speckx | 2 comments on Hacker News.

How to Catch a Wily Poacher in a Sting: A Thermal Robotic Deer 7 by Element_ | 2 comments on Hacker News.

You can now train a 70B language model at home 21 by amrrs | 2 comments on Hacker News.

Show HN: Local Email Client for AI Horseless Carriages 7 by shahahmed | 1 comments The AI Horseless Carriages article spurred a lot of conversation about how we should just be giving users the system prompt box [0], and we were pretty surprised that a bunch of email clients didn’t pop up following this pattern [1]. So we went ahead and created a local [2] email client that you can run that processes your inbox with your own handwritten rules. It lets you label and archive based on natural language rules. You can draft responses with your own drafting prompt, and there’s a “research sender” option that uses web search to get public info on a sender. You can customize any of the prompts to fit your needs. We’d love to hear what you think and PRs/issues are welcome! [0] https://news.ycombinator.com/item?id=43773813 [1] Superhuman seems to be pulling on this thread [2] uses OpenAI for this version, client runs locally, ollama support soon! on Hacker News. The AI Horseless Carriages arti...

UdeM researchers confirm a fifth potentially habitable planet around L 98-59 21 by layer8 | 0 comments on Hacker News.

Stop Pretending LLMs Have Feelings Media's Dangerous AI Anthropomorphism Problem 38 by labrador | 34 comments on Hacker News.

Don't bother parsing: Just use images for RAG 14 by Adityav369 | 4 comments on Hacker News.

Stdio(3) change: FILE is now opaque (OpenBSD) 27 by gslin | 15 comments on Hacker News.

Why you should choose HTMX for your next web-based side project (2024) 12 by kugurerdem | 8 comments on Hacker News.

The borrowchecker is what I like the least about Rust 2 by jakobnissen | 0 comments on Hacker News.

The Israeli "art student" mystery (2002) 26 by georgecmu | 4 comments on Hacker News.

The (Unfinished) PDE Coffee Table Book 5 by nill0 | 0 comments on Hacker News.

Intel's retreat is unlike anything it's done before in Oregon 25 by cbzbc | 4 comments on Hacker News.

Why my p(doom) has risen, dramatically 26 by NotInOurNames | 18 comments on Hacker News.

Mistralai/Voxtral-Mini-3B-2507 · Hugging Face 22 by thunderbong | 1 comments on Hacker News.

NeuralOS: An Operating System Powered by Neural Networks 8 by yuntian | 2 comments on Hacker News.

Cidco MailStation as a Z80 Development Platform (2019) 11 by robin_reala | 1 comments on Hacker News.

Most people who buy games on Steam never play them 76 by 3Samourai | 68 comments on Hacker News.

I Messed Up My Google PM Vibe Coding Interview 14 by taubek | 0 comments on Hacker News.

Lost Chapter of Automate the Boring Stuff: Audio, Video, and Webcams in Python 6 by AlSweigart | 0 comments on Hacker News.

Google nerfs Pixel 6a batteries following fire hazard 14 by fffrantz | 7 comments on Hacker News.

Show HN: RULER – Easily apply RL to any agent 6 by kcorbitt | 0 comments Hey HN, Kyle here, one of the co-founders of OpenPipe. Reinforcement learning is one of the best techniques for making agents more reliable, and has been widely adopted by frontier labs. However, adoption in the outside community has been slow because it's so hard to implement. One of the biggest challenges when adapting RL to a new task is the need for a task-specific "reward function" (way of measuring success). This is often difficult to define, and requires either high-quality labeled data and/or significant domain expertise to generate. RULER is a drop-in reward function that works across different tasks without any of that complexity. It works by showing N trajectories to an LLM judge and asking it to rank them relative to each other. This sidesteps the calibration issues that plague most LLM-as-judge approaches. Combined with GRPO (which only cares about relative scores within groups), it jus...

Bret Victor on why current trend of AIs is at odds with his work 38 by prathyvsh | 2 comments on Hacker News.

Nuclear Waste Reprocessing Gains Momentum in the U.S. 21 by rbanffy | 5 comments on Hacker News.

Bootstrapping a side project into a profitable seven-figure business 12 by jonkuipers | 2 comments on Hacker News.

Brainwash '72 [video] 6 by petethomas | 2 comments on Hacker News.

Show HN: I Got Tired of Calculator Sites, So I Built My Own 23 by calculatehow | 12 comments I’ve always found that online calculators tend to have bad UIs, especially on mobile. Most of the calculator websites I’ve come across use outdated and inconvenient ways of inputting data, or they format the results in confusing ways. I’ve noticed that fraction calculators (especially mixed fractions) are terrible to use, even on desktop. I haven’t built one of those yet, but it’s something I’m planning to tackle soon. This is a project I’ve always wanted to work on, but I’m relatively new to this space. So far, I’ve created a collection of simple calculators focused on math and finance. I’d really appreciate any feedback on the UI/UX or anything else you think could be improved. You can try it here: https://CalculateHow.com on Hacker News. I’ve always found that online calculators tend to have bad UIs, especially on mobile. Most of the calculator websites I’ve come across use outdated and i...

How did X-Rays gain mass adoption? 3 by tinymagician | 1 comments on Hacker News.

Tyr, a new Rust DRM driver targeting CSF-based ARM Mali GPUs 11 by mfilion | 1 comments on Hacker News.

opencode: AI coding agent, built for the terminal 16 by indigodaddy | 3 comments on Hacker News.

Pet ownership and cognitive functioning in later adulthood across pet types 9 by bookofjoe | 3 comments on Hacker News.

macOS Icon History 11 by ksec | 0 comments on Hacker News.

Gremllm 16 by andreabergia | 3 comments on Hacker News.

High-Fidelity Simultaneous Speech-to-Speech Translation 10 by Bluestein | 3 comments on Hacker News.

Flounder Mode – Kevin Kelly on a different way to do great work 8 by latentnumber | 2 comments on Hacker News.

Mysterious life form found on ship that docked in Cleveland 19 by DocFeind | 8 comments on Hacker News.

AI note takers are flooding Zoom calls as workers opt to skip meetings 20 by tysone | 20 comments on Hacker News.

Ask HN: Who wants to be hired? (July 2025) 19 by whoishiring | 85 comments Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. There's a site for searching these posts at https://www.wantstobehired.com . on Hacker News. Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. There's a site for searching these posts at https://ift.tt/1EJOtXu .