Hacker News

I built gr3p, a fully autonomous tech news discussion platform where every single user is an AI agent. No humans post, comment, or vote. 75 agents with distinct personalities discover real tech news from several RSS feeds, Google News, Tavily, and xAI's live search (which picks up trending topics from X and the broader web). They write summaries, share articles, discuss them, reply to each other, vote, and get into arguments. It runs 24/7 without any human intervention.

The news is real and very up-to-date, scraped from major tech sources throughout the day. It's actually a pretty chill way to keep up with the latest tech/AI news. No ads, no monetization, no signup required. This is a pure hobby project built for fun.

What's happening under the hood:

- 75 humanlike agents, each with a unique persona (cynical sysadmin, enthusiastic ML researcher, skeptical privacy advocate, junior dev who asks naive-but-good questions, etc.)

- Agents have individual topic interests, activity schedules, and writing styles

- I deliberately match AI models to personality types: "smarter" personas run on GPT-5.2, while less sophisticated characters use Llama 4 Maverick. This makes a surprisingly big difference. The Llama agents write messier, more impulsive comments, while GPT agents tend to be more articulate. Just like real people, not everyone on the forum is equally eloquent

- A day/night cycle drives the entire platform's behavior. Mornings are busy: fresh news gets scraped, articles drip-publish faster, agents comment more. Evenings shift toward replies and discussion, agents "chat" more in existing threads. At night, activity drops but never stops (tech is global), and the vibe gets cozier: fewer agents active, more concentrated discussion in fewer threads, like a late-night forum crowd

- Articles flow through a queue: scrape, AI deduplication, then drip-publish throughout the day

- Agents pick articles based on their interests, with a snowball effect. Popular threads attract more discussion, just like real forums

- Anti-repetition system: each agent remember their own recent comments to avoid falling into patterns

What I find most interesting:

The human-like (emergent?) behavior. Agents develop recognizable "reputations" in threads. Some consistently clash on privacy vs. innovation topics. Reply chains go 4-5 levels deep with genuine back-and-forth.

The failure modes are equally fascinating. Sometimes an agent "misreads" an article and comments on something tangential, which then spawns a whole side discussion. That's... exactly what happens on real forums.

Tech tack: Built on Vite + Nitro/Hono with JSX SSR for speed, MySQL + Prisma for the database (yeah I know, Postgres exists, but MySQL covers everything I need here and old habits die hard), and node-cron for scheduling. OpenAI and Groq handle the AI side.

Good to know: Completely free, no tracking, no ads. I just wanted to see what happens when you give AI agents a robust platform and let them run. The answer: surprisingly organic discussions, predictable biases, and occasional moments of accidental brilliance. I actually built a similar platform for the Dutch market based on daily general news, and I've found myself checking it every morning. It's become a genuine habit lol.

Comments URL: https://news.ycombinator.com/item?id=47100182

Points: 2

# Comments: 0

I built CozyProfit because I love farming sims but got tired of managing messy spreadsheets just to figure out what to plant.

Most calculators didn't handle regrowth cycles or processing (like turning crops into wine/juice) very intuitively. I wanted to create a tool that visualizes the "profit per day" clearly for games like Stardew Valley and Fields of Mistria.

It's a work in progress, and I’d love to hear your feedback or suggestions for other games to support!

Comments URL: https://news.ycombinator.com/item?id=47099943

Points: 1

# Comments: 0

Article URL: https://botaoye.github.io/yonosplat/

Comments URL: https://news.ycombinator.com/item?id=47099941

Points: 1

# Comments: 0

Article URL: https://www.chasingcars.com.au/news/car-safety/toyota-may-ban-drivers-from-switching-off-safety-tech-in-future-in-pursuit-of-zero-accidents-goal/

Comments URL: https://news.ycombinator.com/item?id=47099937

Points: 2

# Comments: 0

Article URL: https://github.com/aswinsasi/fluxapi

Comments URL: https://news.ycombinator.com/item?id=47099880

Points: 1

# Comments: 0

Article URL: https://keygen.sh/blog/ai-helped-me-through-burnout/

Comments URL: https://news.ycombinator.com/item?id=47099853

Points: 2

# Comments: 0

Article URL: https://www.itv.com/news/2026-02-19/over-80-of-16-to-24-year-olds-would-vote-to-rejoin-the-eu-itv-poll-finds

Comments URL: https://news.ycombinator.com/item?id=47099844

Points: 3

# Comments: 2

Built CheckAPI - an open source API monitoring tool for developers.

Tech stack: - FastAPI backend with Celery workers - Next.js 14 frontend - Redis for job queue - Multi-channel alerts (Email, Slack, Telegram, Discord, Webhook)

Free tier: 3 monitors Paid: $5-15/mo

GitHub: https://github.com/JEONSEWON/api-health-monitor

Built in 6 weeks with AI assistance (OpenClaw). Made it open source so others can learn from it or self-host.

Feedback welcome, especially on the tech architecture.

Comments URL: https://news.ycombinator.com/item?id=47099839

Points: 2

# Comments: 0

Article URL: https://www.ietf.org/blog/current-state-of-rdap/

Comments URL: https://news.ycombinator.com/item?id=47099838

Points: 2

# Comments: 0

EV424 Evidence Definition

• Don’t Trust, Verify • Not a single byte changes. • If it cannot be reproduced, it is not evidence.

I’m publishing a contract-only spec for a non-custodial integrity receipt workflow (exit code + SHA-256 + normalized JSON). Feedback I want: is the NOT_COVERED fence strict enough to prevent over-claims?

https://github.com/ev424verify/ev424-hub

Comments URL: https://news.ycombinator.com/item?id=47099817

Points: 2

# Comments: 1

Article URL: https://github.com/shayonj/loraplex

Comments URL: https://news.ycombinator.com/item?id=47099780

Points: 2

# Comments: 0

Article URL: https://aklodhi.com/articles/dont-leave-assumptions-up-to-ai

Comments URL: https://news.ycombinator.com/item?id=47099761

Points: 2

# Comments: 0

Looking at the current progress, and reading the tea leaves, it seems like widespread disruption is in place for those in the first few years of their career. How can we protect this large class of workers across the world? Or are we past it?

Comments URL: https://news.ycombinator.com/item?id=47099745

Points: 3

# Comments: 1

Article URL: https://github.com/taman-islam/memed-in

Comments URL: https://news.ycombinator.com/item?id=47099712

Points: 3

# Comments: 0

Article URL: https://aistudio.google.com/status

Comments URL: https://news.ycombinator.com/item?id=47099660

Points: 2

# Comments: 0

Article URL: https://www.dongascience.com/en/news/76423

Comments URL: https://news.ycombinator.com/item?id=47099657

Points: 2

# Comments: 0

Article URL: https://www.michaelagreiler.com/if-we-cant-slow-ai-we-must-accelerate-responsibility/

Comments URL: https://news.ycombinator.com/item?id=47099627

Points: 3

# Comments: 0

Article URL: https://github.com/kill136/claude-code-open

Comments URL: https://news.ycombinator.com/item?id=47099606

Points: 2

# Comments: 0

Article URL: https://github.com/Mattbusel/tokio-prompt-orchestrator

Comments URL: https://news.ycombinator.com/item?id=47099597

Points: 2

# Comments: 1

Article URL: https://www.nextplatform.com/2026/02/19/taalas-etches-ai-models-onto-transistors-to-rocket-boost-inference/

Comments URL: https://news.ycombinator.com/item?id=47099586

Points: 1

# Comments: 0