Show HN: adamsreview – better multi-agent PR reviews for Claude Code https://ift.tt/XBinFLg

Show HN: adamsreview – better multi-agent PR reviews for Claude Code I built adamsreview, a Claude Code plugin that runs deeper, multi-stage PR reviews using parallel sub-agents, validation passes, persistent JSON state, and optional ensemble review via Codex CLI and PR bot comments. On my own PRs, it has been catching dramatically more real bugs than Claude’s built-in /review, /ultrareview, CodeRabbit, Greptile, and Codex’s built-in review, while producing fewer false positives. adamsreview is six Claude Code slash commands packaged as a plugin: review, codex-review, add, promote, walkthrough, and fix. I modeled it after the built-in /review command and extended it meaningfully. You can clear context between review stages because state is stored in JSON artifacts on disk, with built-in scripts for keeping it updated. The walkthrough command uses Claude’s AskUserQuestion feature to walk you through uncertain findings or items needing human review one by one. Then, the fix command dispatches per-fix-group agents and re-reviews the work with Opus, reverting any regressions before committing survivors. It runs against your regular Claude Code subscription (Max plan recommended), unlike /ultrareview, which charges against your Extra Usage pool. I would love feedback from Claude Code users, pro devs, and anyone with strong opinions about AI code reviews. Repo: https://ift.tt/VT81R0X Install: /plugin marketplace add adamjgmiller/adamsreview, /plugin install adamsreview@adamsreview https://ift.tt/VT81R0X May 11, 2026 at 07:36AM

Show HN: I trained a chess engine to play like humans https://ift.tt/nHYXWtr

Show HN: I trained a chess engine to play like humans I built 1e4.ai - a chess web app where you play against neural networks trained to mimic human Lichess players at specific Elo ranges. There's a separate model for each 100-point rating bucket from ~800 to 2200+, and the bots not only choose human-like moves but also burn clock time, play worse under time pressure, and blunder in human-like ways. Live demo: https://1e4.ai Code: https://ift.tt/NmLVlrv A few things that might be interesting: - Trained on almost a full year of Lichess blitz games, around 1B total games - Architecture is an a small (~9MM parameters) transformer-based network that takes the board, recent move history, the player's rating, and remaining clock time as input. Three separate models per rating bucket: move, clock-usage, and win probability. The clock model is what makes the bots feel humanish under time pressure rather than instant. Because the move model takes the clock as one input parameter, it also learns to blunder under time pressure like a human might. - Because the network is so tiny, no GPU is needed for inference - it runs easily on a local CPU - Downside of the tiny network is that it's a bit weak as you turn up the rating past around 1700. It can spot short tactics but not long multi-move combinations. - Initial training on a rented 8xH100 cluster, then fine-tunes on my local GPU for different rating ranges - Inspired by Maia-2 and DeepMind's "Grandmaster-Level Chess Without Search". On a held-out Lichess blitz benchmark, the it beats Maia-2 blitz on top-1 move prediction (56.7% vs 52.7%) and pretty substantially on win-probability calibration (Brier 0.176 vs 0.272). Numbers and code in https://ift.tt/SFe81RY... - The data pipeline is C++ via nanobind, then training with Pytorch. Getting this right was actually the thing I spent the most time on. Pre-shuffling the dataset and then being able to read the shuffled dataset sequentially at training time kept the GPU utilization high. Without this it spent a huge percentage of time on I/O while the GPU sat idle. Happy to answer questions about the rating-conditioning, the clock model, or the data pipeline. May 11, 2026 at 04:01AM

Show HN: Hustler Bingo – a tiny bingo game about startup Twitter clichés https://ift.tt/yRxaJoi

Show HN: Hustler Bingo – a tiny bingo game about startup Twitter clichés I built this after my brother started complaining that I got too much into brainrot culture. It's just for fun nothing serious, but was able to test vercel, tanstack start and convex without high stakes. Have fun! This is the game where lower score is goood for your mental health https://ift.tt/RDY4bMJ May 11, 2026 at 02:06AM

Show HN: Mosaic – arrange iOS icons by color using an evolutionary algorithm https://ift.tt/xy6NF3v

Show HN: Mosaic – arrange iOS icons by color using an evolutionary algorithm It started out as a way for me to freshen up my C++ skills during COVID. But life got in the way and it was put on ice. Luckily, coding LLMs came to the rescue and allowed me to bring it to a point where I feel comfortable sharing it. https://ift.tt/bcDNlUp May 10, 2026 at 11:59PM

Show HN: Free OSS transcription app I made and found it's faster than wispr flow https://ift.tt/bKPHtp7

Show HN: Free OSS transcription app I made and found it's faster than wispr flow title doesn't let nuance, ofc it's not the app that's faster but the way you can use it with Groq inference for example. https://mumbli.app/ May 10, 2026 at 03:07AM

Show HN: Create flashcards with Space CLI https://ift.tt/dsQwhDt

Show HN: Create flashcards with Space CLI Hey, I created seven years ago a flashcard app with a main focus on UX. In the last months I added offline-first mode and a CLI that allows Claude Code or Codex to create high quality flashcards for you. I use that to learn about pharma rules, technology, dancing, taxes and smart home. Never really did marketing, this not my specialty. Would love to know what you think https://ift.tt/Htp4DUO May 9, 2026 at 08:08PM

Show HN: tltv – Federation protocol for 24/7 TV channels https://ift.tt/Ce2bBvc

Show HN: tltv – Federation protocol for 24/7 TV channels I spent six years trying to build a tv channel server. rewrote it eight times. flask, fastapi, ffmpeg, gstreamer, named pipes. every version got more complicated and none of them worked right. turns out I was building the wrong thing. the thing I actually wanted was a protocol. so tltv is that. a channel is an ed25519 key pair. you sign your metadata with it. you serve hls video from wherever you want. your public key becomes a tltv:// address that anyone can tune into. relay nodes can re-serve your stream but they can't modify it. they verify signatures on everything. you can move servers and keep your channel because the key is the identity, not the hostname. nodes find each other through peer exchange. no central registry. the cli is probably the fastest way to see what I mean: curl -fsSL timelooptv.org/install | sh tltv keygen tltv server test --name "my channel" -k TV*.key that's a fully compliant origin server. pure go, generates smpte bars with audio, no ffmpeg. one binary, ~20mb of ram. there's also a full gstreamer-based server (cathode), a web viewer (phosphor), and bridge/relay servers in the cli. everything mit licensed. live demo at https://ift.tt/i9elcfQ https://ift.tt/auqwgRA https://timelooptv.org/ May 9, 2026 at 12:58AM