ai Sep 11 Ask HN: Remove Filler LLM Comments Should Online Forums Charge to Filter Out AI-Generated Comments? A Hacker News user posted a proposal this week that cut straight to a problem developers and technical readers have been noticing for months. The post, titled "Remov... ai Sep 11 Serving LLMs on Tenstorrent Hardware: Inside the vLLM TT Plugin vLLM Gets Tenstorrent Support Without Forking the Serving Stack vLLM has added Tenstorrent hardware support through its out-of-tree plugin system, and the interesting part is not that another backend exists. It is that Tenstorrent... programming languages Sep 11 We Replaced MMAP with Io_uring in Our Rust Query Engine. It Got Slower Conviva's query engine hit a wall that looked familiar to anyone running data-intensive workloads on Linux: mmap made everything fast until it didn't. Under concurrent production load, their Rust-based engine saw p95 latency jump... programming languages Sep 11 Advancing Embedded Go: Recoverable Panics, UEFI, Radio and Hardware Dev Kit TinyGo 0.42 landed this week with two things the project has been building toward for years: recoverable runtime panics and a UEFI target that lets Go code run before any operating system boots. Alongside the software release, Tin... ai Sep 11 Show HN: Swiftime - time tracking you can talk to, with an API for AI agents Swiftime is an AI-powered time tracker that replaces manual form-filling with a single sentence. You type or say something like "worked 2.5h on the Acme homepage redesign yesterday from 1pm" and it extracts the client, project, du... ai Sep 11 The Gemini app is now available for Windows Google has released a native Gemini desktop app for Windows 10 and 11, putting its AI assistant a keyboard shortcut away from any active window. The app runs globally and is available for download at gemini.google/desktop. A Globa... ai Sep 11 LiteLLM Alternatives? A recent privilege-escalation vulnerability in LiteLLM has prompted a wave of teams to reevaluate whether running their own LLM gateway is worth the operational cost. CVE-2026-35029, disclosed in early September 2026, allowed a re... ai Sep 11 FinOps for LLM – Leanroute Team wrote a blog When your LLM bill drops 40 percent month to month, the natural reaction is to claim credit for whatever optimization you shipped last sprint. The problem is that usage changes, pricing changes, and architecture changes all move t... ai Sep 11 SAGG – failover gateway for cheap LLM providers SAGG, a DeepSeek gateway provider, published benchmark results measuring whether automatic failover across multiple providers actually reduces request failures in production. The numbers show it does, but unevenly: the gateway's v... ai Sep 11 Anthropic Staffers Again Sound the Alarm on AI Catastrophe A senior AI researcher's resignation from Anthropic has reignited public alarm about the trajectory of frontier AI development. Jacob Coxon, who left the company on Tuesday, wrote that both Anthropic and his previous employer Open...