Measuring the impact of AI on experienced open-source developer productivity

Postgres LISTEN/NOTIFY does not scale

Is Gemini 2.5 good at bounding boxes?

What is Realtalk’s relationship to AI? (2024)

Flix – A powerful effect-oriented programming language

Grok 4

Graphical Linear Algebra

FOKS: Federated Open Key Service

Hey HN, we&#x27;re a YC startup building an open-source, privacy-first alternative to Perplexity Comet.No invite system unlike bunch of others – you can download it today from our website or GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;browseros-ai&#x2F;BrowserOS">https:&#x2F;&#x2F;github.com&#x2F;browseros-ai&#x2F;BrowserOS</a>--- Why bother building an alternative? We believe browsers will become the new operating systems, where we offload much bunch of our work to AI agents. But these agents will have access to all your sensitive data – emails, docs, on top of your browser history. Open-source, privacy-first alternatives need to exist.We&#x27;re not a search or ad company, so no weird incentives. Your data stays on your machine. You can use local LLMs with Ollama. We also support BYOK (bring your own keys), so no $200&#x2F;month plans.Another big difference vs Perplexity Comet: our agent runs locally in your browser (not on their server). You can actually watch it click around and do stuff, which is pretty cool! Short demo here: <a href="https:&#x2F;&#x2F;bit.ly&#x2F;browserOS-demo" rel="nofollow">https:&#x2F;&#x2F;bit.ly&#x2F;browserOS-demo</a>--- How we built? We patch Chromium&#x27;s C++ source code with our changes, so we have the same security as Google Chrome. We also have an auto-updater for security patches and regular updates.Working with Chromium&#x27;s 15M lines of C++ has been another fun adventure that I&#x27;m writing a blog post on. Cursor&#x2F;VSCode breaks at this scale, so we&#x27;re back to using grep to find stuff and make changes. Claude code works surprisingly well too.Building the binary takes ~3 hours on our M4 Max MacBook.--- Next? We&#x27;re just 2 people with a lot of work ahead (Firefox started with 3 hackers, history rhymes!). But we strongly believe that a privacy-first browser with local LLM support is more important than ever – since agents will have access to so much sensitive data.Looking forward to any and all comments!

Show HN: Open source alternative to Perplexity Comet

Red Hat Technical Writing Style Guide

Matt Trout has died

Analyzing database trends through 1.8M Hacker News headlines

Hey HN, Henry and Roman here - we&#x27;ve been building a cross-platform framework for deploying LLMs, VLMs, Embedding Models and TTS models locally on smartphones.Ollama enables deploying LLMs models locally on laptops and edge severs, Cactus enables deploying on phones. Deploying directly on phones facilitates building AI apps and agents capable of phone use without breaking privacy, supports real-time inference with no latency, we have seen personalised RAG pipelines for users and more.Apple and Google actively went into local AI models recently with the launch of Apple Foundation Frameworks and Google AI Edge respectively. However, both are platform-specific and only support specific models from the company. To this end, Cactus:- Is available in Flutter, React-Native &amp; Kotlin Multi-platform for cross-platform developers, since most apps are built with these today.- Supports any GGUF model you can find on Huggingface; Qwen, Gemma, Llama, DeepSeek, Phi, Mistral, SmolLM, SmolVLM, InternVLM, Jan Nano etc.- Accommodates from FP32 to as low as 2-bit quantized models, for better efficiency and less device strain.- Have MCP tool-calls to make them performant, truly helpful (set reminder, gallery search, reply messages) and more.- Fallback to big cloud models for complex, constrained or large-context tasks, ensuring robustness and high availability.It&#x27;s completely open source. Would love to have more people try it out and tell us how to make it great!Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;cactus-compute&#x2F;cactus">https:&#x2F;&#x2F;github.com&#x2F;cactus-compute&#x2F;cactus</a>

Show HN: Cactus – Ollama for Smartphones

Turkey bans Grok over Erdoğan insults

The ChompSaw: A Benchtop Power Tool That's Safe for Kids to Use

Diffsitter – A Tree-sitter based AST difftool to get meaningful semantic diffs

Pangolin is an open source self-hosted tunneled reverse proxy management server with identity and access control, designed to securely expose private resources through encrypted WireGuard tunnels running in user space.We made Pangolin so you retain full control over your infrastructure while providing a user-friendly and feature-rich solution for managing proxies, authentication, and access, all with a clean and simple dashboard web UI.GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;fosrl&#x2F;pangolin">https:&#x2F;&#x2F;github.com&#x2F;fosrl&#x2F;pangolin</a>Deployment takes about 5 minutes on a VPS: <a href="https:&#x2F;&#x2F;docs.fossorial.io&#x2F;Getting%20Started&#x2F;quick-install" rel="nofollow">https:&#x2F;&#x2F;docs.fossorial.io&#x2F;Getting%20Started&#x2F;quick-install</a>Demo by Lawrence Systems (YouTube): <a href="https:&#x2F;&#x2F;youtu.be&#x2F;g5qOpxhhS7M?si=M1XTWLGLUZW0WzTv&amp;t=723" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;g5qOpxhhS7M?si=M1XTWLGLUZW0WzTv&amp;t=723</a>Some use cases:<pre><code> - Grant users access to your apps from anywhere using just a web-browser

 - Proxy behind CGNAT

 - One application load balancer across multiple clouds and on-premises

 - Easily expose services on IoT and edge devices for field monitoring

 - Bring localhost online for easy access
</code></pre>
A few key features:<pre><code> - No port forwarding and hide your public IP for self-hosting

 - Create proxies to multiple different private networks

 - OAuth2&#x2F;OIDC identity providers

 - Role-based access control

 - Raw TCP and UDP support

 - Resource-specific pin codes, passwords, email OTP

 - Self-destructing shareable links

 - API for automation

 - WAF with CrowdSec and Geoblocking</code></pre>

Show HN: Pangolin – Open source alternative to Cloudflare Tunnels

AI coding tools can reduce productivity

Belkin ending support for older Wemo products

Hey HN, I&#x27;m Arkadiy from Leaping AI (<a href="https:&#x2F;&#x2F;leapingai.com">https:&#x2F;&#x2F;leapingai.com</a>). Leaping lets you build voice AI agents in a multi-stage, graph-like format that makes testing and improvement much easier. By evaluating each stage of a call, we can trace errors and regressions to a particular stage. Then we autonomously vary the prompt for that stage and A&#x2F;B test it, allowing agents to self-improve over time.You can talk to one of our bots directly at <a href="https:&#x2F;&#x2F;leapingai.com">https:&#x2F;&#x2F;leapingai.com</a>, and there’s a demo video at <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=xSajXYJmxW4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=xSajXYJmxW4</a>.Large companies are understandably reluctant to have AI start picking up their phone calls—the technology kind of works, but often not very well. If they do take the plunge, they often end up spending months tuning the prompts for just one use-case, and sometimes never even end up releasing the voice bot.The problem is two-sided: it&#x27;s non-trivial to specify the exact way a bot should behave using plain language, and it&#x27;s tedious to ensure the LLM always follows your instructions the way you intended them.Existing voice AI solutions are a pain to set up for complex use cases. They require months of prompting all edge cases before going live, and then months of monitoring and improving prompting afterwards. We do that better than human prompters, and much faster, by running a continuous analysis + testing loop.Our tech is roughly divided into three subcomponents: core library, voice server, and self-improvement logic. Core library models and executes the multi-stage (think n8n-style) voice agents. For the voice server we are using the ol’ reliable cascading way of STT-&gt;LLM-&gt;TTS. We tried out the voice-to-voice models, and although they felt really great to talk to, function-calling performance was expectedly much worse, so we are still waiting for them to get better.The self-improvement works by first taking conversation metrics and evaluation results to produce ‘feedback’, i.e. specific ideas how the voice agent setup could be improved. After enough feedback is collected, we trigger a run of a specialized self-improvement agent. It is a cursor-style AI with access to various tools that changes the main voice agent. It can rewrite prompts, configure a stage to use a summarized conversation instead of a full one, and more. Each iteration produces a new snapshot of the agent, enabling us to route a small part of the traffic to it and promote it to production if things look ok. This loop can be set to run without any human involvement, thus making agents self-improve.Leaping is use-case agnostic, but we currently focus on inbound customer support (travel, retail, real estate, etc.) and lead pre-qualification (medicare, home services, performance marketing) since we have a lot of success stories there.We started out in Germany since that’s where we were in university, but initially growth was challenging. We decided to target enterprise customers right away and they showed reluctance to adopt voice AI as the front-door ‘face’ of their company. Additionally, for an enterprise with thousands of calls daily, it is infeasible to monitor all the calls and tune agents manually. To address their very valid concerns, we put all effort into reliability—and still haven’t gotten around to offering self-serve access, which is one reason we don’t have fixed pricing yet. (Also, with some clients we have outcome-based pricing, i.e. you pay nothing for calls that didn&#x27;t convert a lead, only the ones that did.)Things picked up momentum ever since we got into YC and moved to the US, but the cautious sentiment is also present here if you try to sell to big enterprises. We believe that doing evals, simulation, and A&#x2F;B testing really really well is our competitive edge and what will enable us to solve large, sensitive use cases.We’d love to hear your thoughts and feedback!

Launch HN: Leaping (YC W25) – Self-Improving Voice AI