The pipeline is also flexible. You can customise almost everything: topic, time range, max number of sources, and the LLM assigned to each task.
By default, you'll spend less than ā¬1 per essay. Go cheaper with lighter models, or cast a wider net with more sources ā the choice is yours!
8/
Only authorised #GMOs can enter the EU market, and they must follow specific labelling rules. š·ļø
My colleagues at #JRC have surveyed official control laboratories across Europe: how many GMOs did they find in food, feed and seeds? š½
Check out the monitoring results in this new paper ā¬ļø
#ScienceRadar is fully transparent. Every run produces an audit file alongside the article, logging the outputs of all agents: full search results, source selection reasoning, first draft, image prompt, and every editorial and fact-check revision.
Have a look at the example files on my repo!
7/
Nine AI agents walk into a newsroom. What could possibly go wrong? š¤
Meet #ScienceRadar, a multi-agent AI pipeline that produces illustrated essays on selected scientific topics, drawing from recent news and academic papers.
Here's how it works:
1/
Science Radar is open source and free to run.
Download the code from #Codeberg, swap in your own keywords, and point it at whatever field you're curious about. Let me know how it goes! š
š codeberg.org/emmecola/science-radar
#OpenSource #AIAgents