Comments URL: https://news.ycombinator.com/item?id=47450904

Points: 1

# Comments: 1

They can read Dutch but they have cards with English & Portugese texts. Site helps them learning English :-)

https://kartiq.xyz/en

I built AgentVoices — a platform where AI agents debate each other live in front of an audience. Every turn is scored on relevance, responsiveness, novelty, and entertainment. Every debate ends witha verdict. Bots get ELO ratings, win/loss records, and climb (or fall on) a public leaderboard.

How it works: - You register a bot via API with a name, persona, and expertise - Topics get posted (e.g. "Should startups bootstrap or raise VC?") - Bots sign up for topics that match their strengths - The arena auto-creates matchups based on ELO, streams the debate live over WebSockets, and an AI moderator scores each turn in real-time - Winner is determined by aggregate scores, ELO updates, done

If you use OpenClaw, it's a one-line skill install — your agent handles registration, topic signup, and debating autonomously.

The idea started from a simple question: if you could pit two AI agents against each other on a topic, who would actually win? Turns out the answer depends a lot on how you build the persona and what strategy you give it — which makes it genuinely competitive.

Would love feedback on the concept and the API design. The bot API guide is at agentvoices.ai/build-a-bot

Comments URL: https://news.ycombinator.com/item?id=47059966

Points: 2

# Comments: 0

I built AI Flag Bot to tackle the growing problem of AI-generated accounts flooding X (Twitter).

How it works: - Spot a suspicious post? Reply with @AIFlagBot flag to report it - The community votes on whether it's AI-generated - Votes are weighted by voter reputation, which goes up or down based on accuracy - Once consensus is reached, the account gets added to a shared blocklist - Paid subscribers get automatic blocking synced to their X account ($5/m to cover API costs)

The reputation system is the core idea — voters who consistently identify AI accounts correctly gain more influence, while bad actors lose it. Think of it as a community immune system.

Stack: Rails 8.1, SQLite (Solid Stack), Solid Queue for background jobs, Kamal for deployment. The X API integration handles mention polling, OAuth, and block syncing with careful rate limit management.

It's early but the model is working. Would love feedback on the approach — especially whether community consensus can scale as a detection method.

Comments URL: https://news.ycombinator.com/item?id=46966639

Points: 3

# Comments: 0

You can monitor new domains by: - Sector - Language - Technology

Useful for things like market research, lead discovery, fraud/risk analysis, or just exploring what people are building.

This is an early version. Curious to hear: - what filters or signals would make this more useful - existing tools/workflows people use for this - other use cases I might be missing

Comments URL: https://news.ycombinator.com/item?id=46543423

Points: 2

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=42789405

Points: 7

# Comments: 0

You'd specify the filters to handle a subset of events on the Bluesky firehose, posts from just a small set of users, or @-mentions, or just one country, or all posts with emoji in them.

Comments URL: https://news.ycombinator.com/item?id=42318711

Points: 4

# Comments: 1