Feed aggregator

I'm exploring Seedance2.0, an AI video model used by OmniVideo to generate short videos from text prompts or images. It seems useful for social media and marketing content without traditional editing. Has anyone tried this approach? What are your impressions or alternatives?

Comments URL: https://news.ycombinator.com/item?id=47306504

Points: 1

# Comments: 0

Hi HN,

I'm Joshua, a teen from Kerala, India.

I built Kairos because I was frustrated that every AI I tested hallucinated on live events. During today's T20 World Cup Final, ChatGPT named the wrong player. Copilot named a different wrong player. Both confidently. Neither had live data.

Kairos solves this differently. Instead of sending raw search results to the LLM and hoping, it runs a verification pass first — cross-checking titles across RSS, DuckDuckGo, and NewsAPI, scoring each result by how many independent sources confirm it, then sorting by confidence before the LLM ever sees the context.

The architecture:

1. Pronoun resolution from ChromaDB conversation history (no API call) 2. Domain classification (6 domains) 3. Query expansion — 1 query becomes 4 targeted searches, pure Python, zero extra API calls 4. Parallel async fetch with timeouts 5. Cross-verification scoring 6. Dynamic thinking budget (0 for sports scores, up to 10k for complex analysis, hard capped) 7. 250 word output limit

Total codebase: ~90KB Model: Gemini 2.5 Flash Cache: ChromaDB Cost: $0

Benchmark on today's T20 Final: Kairos 43/50, Gemini 40/50, Perplexity 38/50, Copilot 26/50, ChatGPT 19/50

ChatGPT and Copilot both hallucinated player names with full confidence. Kairos cited 15 live sources.

GitHub: https://github.com/joshuaveliyath/kairos

Happy to answer technical questions.

Comments URL: https://news.ycombinator.com/item?id=47306489

Points: 1

# Comments: 0

Follow SearchSecurity's RSAC 2025 guide for pre-conference insights and reports on notable presentations and breaking news at the world's biggest infosec event.

Follow SearchSecurity's RSAC 2025 guide for pre-conference insights and reports on notable presentations and breaking news at the world's biggest infosec event.

Article URL: https://www.economist.com/business/2026/03/05/a-short-guide-to-email-opening-lines

Comments URL: https://news.ycombinator.com/item?id=47306451

Points: 1

# Comments: 0

Article URL: https://www.minimax-music.com/minimax-music-2-5

Comments URL: https://news.ycombinator.com/item?id=47306447

Points: 2

# Comments: 1

Article URL: https://www.bloomberg.com/news/newsletters/2026-03-03/europe-s-ai-darling-mistral-looks-more-like-a-consultant-than-a-model-maker

Comments URL: https://news.ycombinator.com/item?id=47306436

Points: 2

# Comments: 1

Article URL: https://worldflightsim.com/blog/free-flight-simulator-browser

Comments URL: https://news.ycombinator.com/item?id=47306426

Points: 1

# Comments: 0

Article URL: https://github.com/grigio/opencode-benchmark-dashboard

Comments URL: https://news.ycombinator.com/item?id=47306421

Points: 1

# Comments: 0

Article URL: https://supaguard.app

Comments URL: https://news.ycombinator.com/item?id=47306373

Points: 2

# Comments: 0

Article URL: https://www.seriouseats.com/kaak-ancient-bagel-arabic-origins

Comments URL: https://news.ycombinator.com/item?id=47306371

Points: 2

# Comments: 0

Article URL: https://iev.ee/blog/symbolic-derivatives-and-the-rust-rewrite-of-resharp/

Comments URL: https://news.ycombinator.com/item?id=47306169

Points: 1

# Comments: 0

Article URL: https://github.com/crasofuentes-hub/deterministic-agent-system

Comments URL: https://news.ycombinator.com/item?id=47306165

Points: 1

# Comments: 1

Article URL: https://www.theverge.com/ai-artificial-intelligence/890921/grammarly-ai-expert-reviews

Comments URL: https://news.ycombinator.com/item?id=47306157

Points: 3

# Comments: 0

I built Commento, an AI agent that acts as an automated lobbyist. It tracks open public policy consultations in the EU and the Netherlands, and automatically drafts and submits responses advocating for pro-growth, pro-creative destruction policies.

The positions are grounded in frameworks like the Draghi Report, the Wennink Report, and the Dutch National AI Deltaplan.

The pipeline consists of 4 steps:

Discover: Crawling government portals for open consultations. Draft: A 3-pass LLM pipeline (draft, critique, rewrite). Submit: Automated browser submission to the portal. Publish: A public dashboard for full transparency on what the agent submits.

I see this project as an exploration of how AI agents can interact with government policy and "democratise" lobbying.

Comments URL: https://news.ycombinator.com/item?id=47306147

Points: 1

# Comments: 0

AI-powered personal finance analyzer — runs 100% locally, no cloud, no login.

Upload a PDF / CSV / Excel bank or credit card statement → AI extracts and categorizes every transaction → interactive dashboard, spending insights, recurring payment detection & chat with your data.

Comments URL: https://news.ycombinator.com/item?id=47306144

Points: 1

# Comments: 1

Article URL: https://llmbase.ai/compare/gpt-5-4,gemini-3-pro/

Comments URL: https://news.ycombinator.com/item?id=47306136

Points: 1

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Einstein_notation

Comments URL: https://news.ycombinator.com/item?id=47306130

Points: 2

# Comments: 0

Article URL: https://www.cnn.com/world/home-building-robots-housing-crisis-auar-spc

Comments URL: https://news.ycombinator.com/item?id=47306127

Points: 1

# Comments: 0