//
sign in
Profile
by @danabra.mov
Profile
by @dansshadow.bsky.social
Profile
by @jimpick.com
AviHandle
by @danabra.mov
AviHandle
by @dansshadow.bsky.social
AviHandle
by @katherine.computer
EventsList
by @katherine.computer
ProfileHeader
by @dansshadow.bsky.social
ProfileHeader
by @danabra.mov
ProfileMedia
by @danabra.mov
ProfilePlays
by @danabra.mov
ProfilePosts
by @danabra.mov
ProfilePosts
by @dansshadow.bsky.social
ProfileReplies
by @danabra.mov
Record
by @atsui.org
Skircle
by @danabra.mov
StreamPlacePlaylist
by @katherine.computer
+ new component
Profile
Loading...









Loading...
Bioinformatician and IT consultant - ITA/ENG Sono più attivo su Mastodon, seguitemi lì: https://sayansi.social/@emmecola 🇮🇹 https://fediscience.org/@emmecola 🌍 https://l.devol.it/@emmecola
Moreno Colaiacovo 🇪🇺
Finally, one last artistic touch. Illustrator Agent, it's your turn! The team's creative mind reads the article and crafts a prompt for image generation, evocative and deliberately sparse on details (too many specifics tend to produce very bad images). 6/
1mo
Moreno Colaiacovo 🇪🇺
Nine AI agents walk into a newsroom. What could possibly go wrong? 🤖 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/
1mo
#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/
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 €1 per essay. Go cheaper with lighter models, or cast a wider net with more sources — the choice is yours! 8/