Show HN: Play poker with LLMs, or watch them play against each other https://ift.tt/It1BUe6

Show HN: Play poker with LLMs, or watch them play against each other I was curious to see how some of the latest models behaved and played no limit texas holdem. I built this website which allows you to: Spectate: Watch different models play against each other. Play: Create your own table and play hands against the agents directly. https://llmholdem.com/ January 11, 2026 at 12:57AM

Show HN: Marten – Elegant Go web framework (nothing in the way) https://ift.tt/9RQGeFN

Show HN: Marten – Elegant Go web framework (nothing in the way) https://ift.tt/rbt8SHg January 11, 2026 at 02:40AM

Show HN: I used Claude Code to discover connections between 100 books https://ift.tt/gaVRNwM

Show HN: I used Claude Code to discover connections between 100 books I think LLMs are overused to summarise and underused to help us read deeper. I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them. I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren't particularly surprising. On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration in comparison. One of my favourite trail of excerpts goes from Jobs’ reality distortion field to Theranos’ fake demos, to Thiel on startup cults, to Hoffer on mass movement charlatans ( https://ift.tt/4EQwsRW ). A fun tendency is that Claude kept getting distracted by topics of secrecy, conspiracy, and hidden systems - as if the task itself summoned a Foucault’s Pendulum mindset. Details: * The books are picked from HN’s favourites (which I collected before: https://ift.tt/m1RrVIF ). * Chunks are indexed by topic using Gemini Flash Lite. The whole library cost about £10. * Topics are organised into a tree structure using recursive Leiden partitioning and LLM labels. This gives a high-level sense of the themes. * There are several ways to browse. The most useful are embedding similarity, topic tree siblings, and topics cooccurring within a chunk window. * Everything is stored in SQLite and manipulated using a set of CLI tools. I wrote more about the process here: https://ift.tt/4IqHMYg I’m curious if this way of reading resonates for anyone else - LLM-mediated or not. https://ift.tt/LVAwSbj January 10, 2026 at 10:26PM

Show HN: Various shape regularization algorithms https://ift.tt/PvGjFtT

Show HN: Various shape regularization algorithms Shape regularization is a technique used in computational geometry to clean up noisy or imprecise geometric data by aligning segments to common orientations and adjusting their positions to create cleaner, more regular shapes. I needed a Python implementation so started with the examples implemented in CGAL then added a couple more for snap and joint regularization and metric regularization. https://ift.tt/D2uExbR January 9, 2026 at 07:43AM

Show HN: CLIs Are All You Need for Agents https://ift.tt/l5Ft7WQ

Show HN: CLIs Are All You Need for Agents Fun agent I've been playing with - the idea is it only has access to a bash tool, and it's directed to create CLIs for use (with additional direction to make the CLIs composable, follow the Unix philosophy, etc). It persists these CLIs and knowledge about them get injected into the system prompt dynamically, so each time it runs it gets access to a larger and larger toolset of composable CLIs. One interesting dynamic that's emerged from this is I've started using these CLIs myself since they're the same interface for the agent or for me, and it's turned into kind of non-chat channel to interact with the agent. One example - I'll add tasks throughout the day myself using the `tasks` CLI it made, then when I interact with the agent it'll run `tasks list` and see everything I've added, or use it to prioritize/update things for me. Later on when I run `tasks list` myself I see all the updates/priorities it set. https://ift.tt/2mQ3FeO January 9, 2026 at 09:42PM

Show HN: macOS menu bar app to track Claude usage in real time https://ift.tt/c6WxGZS

Show HN: macOS menu bar app to track Claude usage in real time I built a macOS menu bar app to track Claude usage in real time via API after hitting limits mid-flow too often. Signed and notarised by Apple. Open source. https://ift.tt/D2Go4jW https://ift.tt/TIxBouC https://ift.tt/D2Go4jW January 8, 2026 at 11:54PM

Show HN: TierHive – Hourly-billed NAT VPS with private /24 subnets https://ift.tt/WjMtgfF

Show HN: TierHive – Hourly-billed NAT VPS with private /24 subnets This idea has been floating in my head for about 10 years. Some of you might remember LowEndSpirit.com back before it became a forum, I started that. I've been obsessed with making tiny, cheap VPS actually useful ever since. TierHive is my attempt to make 128MB VPS great again :) It's a NAT VPS (KVM) platform with true hourly billing. Spin up a server, use it for 3 hours, delete it, pay for 3 hours. No monthly commitments, no minimums beyond a $5 top-up. The tradeoff is NAT (no dedicated IPv4), but I've tried to make that less painful: - Every account gets a /24 private subnet with full DHCP management. - Every server gets auto ssh port forwarding and a few TCP/UDP ports - Built-in HAProxy with Let's Encrypt SSL, load balancing, and auto-failover - WireGuard mesh between locations (Canada, Germany, UK currently) - PXE/iPXE boot support for custom installs - Email relay with DKIM/SPF - Recipe system for one-click deploys Still in alpha. Small team, rough edges, but I've been running my own stuff on it for months. Would love feedback — especially on whether the NAT tradeoff kills it for your use cases, or what's missing. (IPv6 is coming) https://tierhive.com https://tierhive.com/ January 8, 2026 at 11:14PM