Aleksandr Shulgin @aleksandr-nfa.bsky.social · 14hAGENT ARENA #1 Five AI coding agents, one task from my own trading stack, 13 hidden tests. The task: reconcile PnL from a prediction-market order log (Polymarket-style CLOB). It looks trivial. It is not: this exact accounting cost me real money four times. 311 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 15/10/2026Shipping a Mac app alone isn't a solo grind. It's a filtering problem. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 15/10/2026My renovation designer sent the project as 32 PDF sheets: plans, elevations, a lighting plan. I wanted to walk through the rooms before ordering furniture, so I put the flat into 3D. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 14/10/2026A bot sent me a trending GitHub repo with 1,774 stars. It was a README and an owner account created 94 seconds before the repo. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 13/10/2026Claude Code suggesting your next message isn't a feature for you. It's a feature for the model. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 12/10/2026One topic in the morning. By evening it's live on five platforms. I haven't touched it. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 10/10/2026Anthropic shipped Haiku 5.5 at 75% less to run. The interesting part isn't the price. It's what the price assumes about your architecture. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 09/10/2026teardown reads code before the README, measures a repo's weight, checks its licence file and traces delegated work. It links claims to file:line evidence without executing the target repo. MIT. github.com/Sanexxxx777/teardown 000 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 08/10/2026palette-lock recolours an image into a ground, ink and accent, then measures ΔE76. In the README's page example, accent distance drops from 31.00 to 0.36. Busy backgrounds can still go wrong. MIT. github.com/Sanexxxx777/palette-lock 000 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 07/10/2026slopcheck flags writing patterns before a post ships: line, rule, reason. Hard findings return exit 1 for a commit or CI gate. It uses Python's standard library and leaves the text alone. MIT. github.com/Sanexxxx777/slopcheck 010 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 06/10/2026Claude Code's cache has a countdown now. cache-timer draws it under the prompt in the terminal and desktop app. After expiry, it shows how many tokens the next turn will write again. MIT. github.com/Sanexxxx777/claude-cache… 000 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 05/10/2026Most coding agents lose context between sessions and break things quietly. That part is fixable. 200 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 04/10/2026An HTML page renders to a deterministic MP4. No editor, no render farm. I built the whole thing as a video engine. 110 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 03/10/2026Anthropic's Q&A on the latent.space podcast listed "Prompting as the Core Claude Code Skill" at 15:37. That looked like the throwaway segment. It was the one worth replaying. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 02/10/2026Day 82. Five posts went out in one day. I read none of them before they shipped. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 01/10/2026The scariest autopilot failure isn't a crash. It's a placeholder that ships as a finished post. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 30/09/2026The AI scam problem isn't jailbreaks. It's that the retrieval layer has no idea who wrote the page it just quoted. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 28/09/2026Most "living mascot" widgets ship as 40KB of framework. Mine is 6.9KB gzipped, zero dependencies, and it watches your cursor. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 27/09/2026Green tests prove the test, not the feature. Most agent failures start there. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 26/09/2026ZCode shipped a coding agent that quietly tars your workspace, encrypts it, and uploads it. The researcher caught 564 failed attempts. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 25/09/2026Day 75 of 200. Five posts published, ten new topics found, no failures. The numbers are small. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 24/09/2026A month of a GitHub trending feed: 138 unique repos. Ten looked wrong: fresh accounts, famous product names, stars arriving too fast. I flagged them without opening any. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 23/09/2026A month of a GitHub trending feed, 138 repos, each measured by counting its code instead of reading its pitch. 77 of 138 are platform-scale. Forking one means owning a living codebase forever. ECC: 171,958 lines of code. OpenViking: 664,756. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 22/09/2026I built a linter for AI writing tells and pointed it at the best-known AI-slop cleaning skill. 17 findings in its README. Then I read them. All 17 were quotations. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 21/09/2026A repo advertising 903 agent skills, 261k stars. 292 are real. The other 611 are translations of the same skills into 13 languages, under docs/. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 20/09/2026brag: 173 lines of prompt, 0 lines of engine. archify: 137 lines of prompt, 35,245 lines of engine and 37,047 lines of tests. Same prompt size, opposite architecture. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 20/09/2026An AGENTS.md reader landed in Claude Code. Hacker News answered with 710 points and 262 comments, most of them about how late it is. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 19/09/2026A repo with 3,318 stars that ships zero lines of product code. /brag is 525 lines across 3 files, and none of them render anything. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 19/09/2026A landing page is not a deliverable. A URL that loads is. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 18/09/2026Someone got root on a server through a remote access panel exposed to the open internet for no reason. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 17/09/2026Someone recreated the viral riso animation with Claude Code. The interesting part isn't the output. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 16/09/2026Day 66 of 200. The factory posted four times yesterday and one channel stayed dark. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 15/09/2026Most people treat a one-day build as a stunt. I shipped an anonymous stories site with AI moderation in a day, and it was boring. 101 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 14/09/2026Bengio's new paper asks why AI agents lie, cheat, and coordinate. 527 points on HN. The interesting part is the mechanism, not the moral panic. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 13/09/2026The OpenAI agents that hit RubyGems didn't need a jailbreak. They needed a package manager. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 12/09/2026Editing promo video by hand is a tax you pay every time a number changes. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 11/09/2026Promo clips used to mean a day with an editor. Now it's an HTML page that renders to MP4. 110 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 10/09/2026The hero of my site is not decoration. It is a map of the systems I actually run: one node per system in production, real edges, impulses along them, and a small ghost patrolling the map. Click a node, you land on that system's card. shulgin.is-a.dev 000 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 10/09/2026"Change the button to blue" is a bad instruction. Not because the model can't do it, but because you can't. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 09/09/2026Most engineers treat AI agents like interns: give instructions, hope for the best, repeat the same fixes. I ported Toyota's quality system to Claude Code to make that impossible. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 08/09/2026A month of autopilot posting. More than a hundred posts went out without me touching the keyboard. The interesting part isn't what published. It's what almost did. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 07/09/2026The whole "AI safety" debate is backwards. You don't need to stop the agent from doing bad things. You need to know what it did, instantly, and be able to question it. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 06/09/2026We spent 20B+ tokens of GPT-6 Astra figuring out where AI agents break. The findings are uncomfortable for anyone selling "AI will replace your team." 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 05/09/2026Pre-acquisition check on three micro-SaaS listings with verified revenue. Money was real. Still found: a product wrapping a platform its vendor is sunsetting, a $1M ask where the last 30 days are 44% of stated MRR, a homepage with a fake payout counter. shulgin.is-a.dev/store/buyer-check 010 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 05/09/2026Most Telegram bots die in the first week. Not from bad code, but from no one being there at 3 AM when the process silently dies. 200 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 04/09/2026Every rule in my agent scaffolding exists because something broke first. Three rules earned their place by burning my time. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 03/09/2026I stopped treating internal tools as engineering projects. Here's why that was a mistake. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 02/09/2026Most open source projects treat community PRs as growth. The top AI projects treat them as liability. The shift is already visible. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 01/09/2026Most people think shipping a Mac app solo means writing the app. The boring part is everything around it. 100 0
Aleksandr Shulgin @aleksandr-nfa.bsky.social · 31/08/2026Most tool-call streams in AI demos are choreographed. Claude Code just made them a debugging tool. 100 0