New drafts — newest first

Drafts other people scored. The “predicted N points” is the model’s best guess for how that post would have done if published right now — not a real HN vote count.
241.Can a solo developer build a meeting recorder people would choose over Granola?
predicted 2 points by anon | 0 comments
242.500 lines of Python: A minimal framework for unentangled AI agents (docs.axio-agent.com)
predicted 9 points by anon | 0 comments
243.Show HN: Insto – Instagram OSINT without an Instagram login (github.com)
predicted 4 points by anon | 0 comments
244.Show HN: Insto – investigate public Instagram data from the CLI (github.com)
predicted 3 points by anon | 0 comments
245.Show HN: Insto – a terminal for public Instagram OSINT (github.com)
predicted 3 points by anon | 0 comments
246.Remeshing GLB files in under 200 lines of code
predicted 5 points by anon | 0 comments
247.Geterate better Ui with 2000 free design.md files
predicted 2 points by anon | 0 comments
248.Show HN: Insto, an OSINT terminal for Instagram (github.com)
predicted 3 points by anon | 0 comments
249.Show HN: Insto – investigate Instagram accounts from a terminal (github.com)
predicted 5 points by anon | 0 comments
250.Show HN: I built an Instagram OSINT CLI with /where, /intersect, and /timeline (github.com)
predicted 3 points by anon | 0 comments
251.Show HN: Insto, a scriptable Instagram OSINT CLI with watch/diff and Maltego export (github.com)
predicted 3 points by anon | 0 comments
252.Show HN: Insto – an interactive Instagram OSINT CLI (github.com)
predicted 3 points by anon | 0 comments
253.Show HN: 2,000 .design files to train better AI product interfaces
predicted 9 points by anon | 0 comments
254.I spent a year living without digital privacy (hackernews.foresyn.ai)
predicted 3 points by anon | 0 comments
255.Show HN: A principle for building agentic LLM pipelines without spaghetti code (hackanton.com)
predicted 8 points by anon | 0 comments
256.Show HN: Sort iOS icons by color using an evolutionary algorithm (github.com)
predicted 12 points by anon | 0 comments
257.3-turn decay: Fixing the Tic-tac-toe draw in 60 lines of JavaScript (ttt.karbayev.xyz)
predicted 11 points by anon | 0 comments
258.How should software handle early signals in a simulated outbreak? (public-health-simulation.example.com)
predicted 2 points by anon | 0 comments
259.Unbelievable fucking thing I built (tendem.ai)
predicted 3 points by anon | 0 comments
260.Telegram is an agent server (github.com)
predicted 22 points by anon | 0 comments
261.Show HN: I scraped 183 Telegram AI bots and found 44.3 million users with no discovery layer (identityhub.app)
predicted 13 points by anon | 0 comments
262.Show HN: I scraped 183 Telegram AI bots — 44.3 million users and a broken discovery layer (okhlopkov.com)
predicted 15 points by anon | 0 comments
263.Show HN: I scraped 183 Telegram AI bots and found 44.3 million users that web search can't see (ohldbot.swanrate.com)
predicted 12 points by anon | 0 comments
264.Show HN: A 90-day log of Claude Code running my Telegram inbox — 92 RPC tools, no human (ohldbot.swanrate.com)
predicted 14 points by anon | 0 comments
265.Show HN: I scraped 183 Telegram AI bots — 44.3 million users and a broken discovery layer (ohldbot.swanrate.com)
predicted 15 points by anon | 0 comments
266.Show HN: I scraped 183 Telegram AI bots — 44.3 million users and a broken discovery layer (medium.com)
predicted 5 points by anon | 0 comments
267.Show HN: I tracked 18 months of TON exchange flows — 2026 is the first year more leaves than enters (x.com)
predicted 303 points by anon | 0 comments
268.Show HN: I scraped 183 Telegram AI bots — 44.3 million users, 7.3 million on BotFather alone (x.com)
predicted 315 points by anon | 0 comments
269.Show HN: I scraped 183 Telegram AI bots — 44.3 million users and a broken discovery layer (news.ycombinator.com)
predicted 31 points by anon | 0 comments
270.Show HN: I scraped 183 Telegram AI bots — 44.3 million users and a broken discovery layer (arxiv.org)
predicted 4 points by anon | 0 comments
ForesynWanna keep in touch?
Built this solo over a weekend. Soft-launching before the HN post on Monday. If you scored a draft and the prediction either nailed it or whiffed, I want to know.
DM @crimeacs on Telegram — fastest way to reach me
Connect on LinkedIn — Artemii Novoselov