Buy A Modem

Show HN: Pencil Puzzle Bench – LLM Benchmark for Multi-Step Verifiable Reasoning

I've been working on applying LLMs to long-context, verifiable problems over the past year, and today I'm releasing a benchmark of 62,000 pencil puzzles across 94 types (sudoku, nonori, slitherlink, etc.). The benchmark also allows for intermediate checks /rule breaks for all varieties at any step.I tested 51 models against a subset (300 puzzles) in two modes: single-shot (output the full solution) and agentic (iterate with verifier feedback).Some results:- Best model (GPT 5.2@xh

Show HN: Demucs music stem separator rewritten in Rust – runs in the browser

Hi HN! I reimplemented HTDemucs v4 (Meta's music source separation model) in Rust, using Burn. It splits any song into individual stems — drums, bass, vocals, guitar, piano — with no Python runtime or server involved.Try it now: https://nikhilunni.github.io/demucs-rs/ (needs a WebGPU-capable browser — Chrome/Edge work best)GitHub: https://github.com/nikhilunni/demucs-rsIt runs three ways:- In the browser — the full ML inference pipeline compiles

Ask HN: What is the state of prompt injection attacks and best practices?

I am curious about the state of prompt injection attacks on frontier models. Are they still vulnerable? For example, is it safe to let Claude Code look at user-submitted data if it also helps manage some of the infrastructure or code? Can they just be asked to identify prompt injection attacks and flag and ignore them, or do injection attacks change the models' behavior despite the owner's prompts? What are best practices?

Show HN: My colleague said my prompts were unreadable. I built a prompt builder

Last week I started using Claude Code. My colleague, who has been prompting AI models for months, looked at what I was sending and said he had no idea what I was asking for.If an experienced user couldn't parse it, the model definitely wasn't getting the best version of it either.So I built flompt. The idea is simple: instead of writing a prompt as a wall of text, you decompose it into typed visual blocks (role, context, objective, constraints, examples, output format), arrange them, a

Show HN: I built a LLM human rights evaluator for HN (content vs. site behavior)

I built Observatory to automatically evaluate Hacker News front-page stories against all 31 provisions of the UN Universal Declaration of Human Rights — starting with HN because its human-curated front page is one of the few feeds where a story's presence signals something about quality, not just virality. It runs every minute: https://observatory.unratified.org. Claude Haiku 4.5 handles full evaluations; Llama 4 Scout and Llama 3.3 70B on Workers AI run a lighter free-tier pass.M

Show HN: Augur – A text RPG boss fight where the boss learns across encounters

I've been building Augur as a solo side project for the last month or so. It started as an experiment to see if I could make "boss fight" that learned from all comers, but still felt genuinely fair to play. The original plan was to build a simplistic jrpg style turned-based encounter engine, but I quickly pivoted to a text based interface, recalling my early experiences with Adventure and Zork. That naturally led to incorporating an LLM, and it turned into something I find pretty

Tell HN: We modeled the cost of boilerplate (it's ~80% of the budget)

We spent the last month modeling software budgets to figure out why velocity often feels so low even with senior teams. The short answer seems to be structural: about 80% of engineering time goes to non-differentiating infrastructure (auth, pipelines, CRUD) rather than unique business logic.We call it the "Infrastructure Tax." We analyzed an anonymized $2.4M engineering spend, and honestly, the breakdown was depressing. Only about 20% of that budget went to features that actually diffe

Show HN: Liftstack – Snippet-level A/B testing for CRM marketers

I've spent years in CRM and email marketing, and one thing has always driven me mad: the constant pressure from the business to "test everything" when you know damn well you'll never reach statistical significance.Most ESP's use frequentist models. You need a fixed sample size calculated upfront, you can't peek at results early without inflating your false positive rate, and if your list isn't massive, you're waiting weeks for a result that often comes bac

Show HN: DailyStack – Aggregate your work tools into a 5-minute morning brief

Hey HNI’m one of the founders of DailyStack.Like many of you, my workday used to start with a "tab crawl." I’d open Gmail, then Outlook for the corporate stuff, then scan Todoist, check the Linear board for dev tickets, and finally peek at Asana for the marketing syncs. By the time I actually knew what my day looked like, I’d already context-switched five times and lost the "deep work" window of my morning.We built DailyStack to solve this. It’s a single, high-signal brief th

EdgeQ Bases AI-Enhanced 5G Modems on RISC-V

5G and artificial intelligence (AI) startup EdgeQ today announced that its upcoming modems will be built on the RISC-V architecture. This approach allows machine learning inference capabilities to be ...

Starlink vs Fiber Internet: The Ultimate Comparison for Speed, Latency, and Reliability

Compare Starlink vs fiber in this clear satellite vs fiber internet broadband comparison covering real‑world speed, latency, reliability, and availability to help you choose the best connection.

Fiber vs. Cable: Which Internet Type Is Best + Pros and Cons

Fiber vs. Cable: Which Internet Type Is Best + Pros and Cons Your email has been sent Key takeaways Fiber is faster, highly reliable, more durable, and great for ...

Best rural internet providers of 2025: Fastest options for small towns & remote homes

National providers like Spectrum, T-Mobile, Starlink, and Hughesnet offer cable, 5G, and satellite solutions. Regional providers such as Frontier, AT&T, Rise Broadband, and Ziply Fiber are expanding ...

Comparing the best high-speed internet providers of 2025: Speeds, plans and availability

High-speed internet in 2025 is defined by download speeds of at least 100 Mbps, with some fiber plans reaching 8 Gbps. Top providers like Google Fiber and AT&T offer symmetrical fiber speeds, while ...