Community

Join Our Community

Connect with researchers, practitioners, and enthusiasts passionate about AI safety.

Two ways to take part

Stay up to date

Follow events, discussions and opportunities in our Discord, and receive our updates.

Contribute to a working group

Sign up and join the Discord
Pick a working group
Contribute

See the working groups →

Both paths start from the same form. Once your sign-up is accepted, you'll get access to the Discord.

Where we are

We are spread across Italy, with members in universities, companies, and independent research. Most of us met online and now run study groups, seminars, and events wherever there are enough of us to fill a room.

Part of the community works abroad, which is how we stay connected to the wider AI safety field.

Community Members

People who have joined the community and agreed to be listed.

Last updated: 2026-10-07

Name	Location	Areas of Interest
Angelo Leone	Londra, Regno Unito	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale
Luca Mattiazzi grokked.it	Milano, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Sicurezza informatica per modelli di frontiera
Cristian Curaba cristian-curaba.github.io/	Udine, Italia
Madhusudhan Pathak myspy.vercel.app/	Padova, Italy	Alignment (RLHF, scalable oversight, value alignment), Etica dell'AI e impatto sociale
Lorenzo Pacchiardi lorenzopacchiardi.me/	Cambridge, United Kingdom	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Rischi catastrofici / esistenziali
Raffaele Mura rmura498.github.io/	Cagliari, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML, AI governance e policy, Sicurezza informatica per modelli di frontiera
Giulia Consonni linkedin.com/in/gconsonni/ github.com/joleencfh/	Neustadt (Weinstr.), Germania	Rischi catastrofici / esistenziali
Luca Scionis linkedin.com/in/luca-scionis-148b37251/	Cagliari, Italia	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Robustness e adversarial ML
Giovanni Occhipinti linkedin.com/in/occhipintigiovanni github.com/Joe-Occhipinti scholar.google.com/citations?hl=it&view_op=list_works&gmla=AIqSsVvv-UWkc_1GO81G7DLSWJR_-QuSCtoSjW4WWgfnizSwlf7S68xhXSKiPprPDZLtYP_RcbFWGELDVM9azolz&user=2vWR8IAAAAAJ	Bologna, Italia	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, Rischi catastrofici / esistenziali
Battista Biggio battistabiggio.github.io/	Cagliari, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML
Elisabetta Rocchetti linkedin.com/in/elisabetta-rocchetti-70a953143/ eliroc98.github.io/	Milano, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.)
Bernardo Manfriani linkedin.com/in/bernardomanfriani/	Firenze, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), AI governance e policy, Etica dell'AI e impatto sociale
Giuseppe Birardi lesswrong.com/users/giuseppe-birardi linkedin.com/in/giuseppe-birardi-18a7b011/ scholar.google.com/citations?hl=en&user=-Be-HhwAAAAJ	Bari, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, Etica dell'AI e impatto sociale
Gabriele Sarti gsarti.com	Bremen, Germania	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking)
Alberto Cazzaniga	Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking)
Lionel Tzatzkin lionelt.dev	Castiglione del Lago (PG), Italy	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Etica dell'AI e impatto sociale
Niccolò Manfredi Selvaggi linkedin.com/in/niccolò-manfredi-selvaggi?utm_source=share_via&utm_content=profile&utm_medium=member_android	Torino, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking)
Emanuele Marconato emanuele-marconato.github.io/	Trento, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Nicola Novello nicolanovello.github.io/	Klagenfurt, Austria	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML, Etica dell'AI e impatto sociale
Giovanni Duca r3lativo.github.io/	Paris, France	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), Etica dell'AI e impatto sociale
Orazio Oztas github.com/oraziooztas	Torino, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML
Daniele Pace danielepace.tech/	London, United Kingdom	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment)
Leonardo Piano linkedin.com/in/leonardo-piano-17663a1aa/ github.com/leonardoPiano	Cagliari, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Robustness e adversarial ML
Yasmin Bougammoura	Hannover, Germania	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, AI governance e policy, Etica dell'AI e impatto sociale, Sicurezza informatica per modelli di frontiera
Edoardo Cecchinato linkedin.com/in/edoardo-cecchinato-4799a9247/	Trento, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Etica dell'AI e impatto sociale
Riccardo Conte linkedin.com/in/riccardoconte-cybersecurity/	Orebro, Svezia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML, AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Enrico Bottazzi leku.ink/	Bergamo, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.)
Maura Pintor maurapintor.github.io	Cagliari, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, AI governance e policy, Sicurezza informatica per modelli di frontiera
Matteo Gallo linkedin.com/in/matteo-galloai	Trieste, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Francesco Diana francescodiana99.github.io/	Nice, Francia	Robustness e adversarial ML, Etica dell'AI e impatto sociale, Sicurezza informatica per modelli di frontiera
Fabio Brau fabiobrau.github.io/	Cagliari, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML
Carlo Martinucci linkedin.com/in/carlomartinucci carlomartinucci.substack.com	Padova, Italia	Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Akash Mittal linkedin.com/in/akash-mittal/	Milan, Italy	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Daniele Federico Rosa linkedin.com/in/danielefedericorosa/	Roma, Italia	Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Gerson Enriquez linkedin.com/in/gerson-enriquez/	Milano, Italia	Alignment (RLHF, scalable oversight, value alignment), Etica dell'AI e impatto sociale, Sicurezza informatica per modelli di frontiera, Rischi catastrofici / esistenziali
Maria Beatrice Panico linkedin.com/in/maria-beatrice-panico-09337b84/	Londra, Gran Bretagna	AI governance e policy, Etica dell'AI e impatto sociale
Eleonira Giunchiglia profiles.imperial.ac.uk/e.giunchiglia	London, United Kingdom	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), Rischi catastrofici / esistenziali
Michele Luca Contalbo linkedin.com/in/luca-contalbo-31894421b/	Reggio Emilia, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Robustness e adversarial ML
Daniele Potertì scholar.google.com/citations?user=S071miUAAAAJ&hl=it	Singapore	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking)
Stefano Pisciotta linkedin.com/in/stefano-pisciotta1/	Torino, Italia	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, Sicurezza informatica per modelli di frontiera, Rischi catastrofici / esistenziali
Lucia Cerulo	Bologna, Italia	Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Jacopo Zacchigna jac-zac.github.io/	Trieste, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.)
elettra decise linkedin.com/in/elettra-decise github.com/eledecise	torino, italia	Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, AI governance e policy, Etica dell'AI e impatto sociale, Sicurezza informatica per modelli di frontiera
Daniele La Ciura linkedin.com/in/daniele-la-ciura/	Milano, Italia	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Etica dell'AI e impatto sociale
Federica Marocco linkedin.com/in/federica-marocco	Torino, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale, Sicurezza informatica per modelli di frontiera
Aldo Pisano aldopisano.github.io/	Catania, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), AI governance e policy, Etica dell'AI e impatto sociale
Michele Canarino linkedin.com/in/mcanarino?utm_source=share_via&utm_content=profile&utm_medium=member_ios	Roma, Italia	Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Ettore Matsaganis	Milano, Italia	AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Igor Maljkovic linkedin.com/in/igor-maljkovic-875b02264/	Genova, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML, Sicurezza informatica per modelli di frontiera
Marco Zoppetti linkedin.com/in/marco-zoppetti-a560aa39b	Borgosesia, Italia	Evaluation (capability evaluations, dangerous capability evals, benchmarking), AI governance e policy, Etica dell'AI e impatto sociale
Fabio Spagliardi linkedin.com/in/fabiospagliardi github.com/fabiospagliardi scholar.google.com/citations?user=T75Q7TYAAAAJ&hl=en	Milano/Bergamo, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Rischi catastrofici / esistenziali
Cristoforo Caffi linkedin.com/in/cristoforo-caffi-80079b86	Firenze, Italy	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, AI governance e policy, Etica dell'AI e impatto sociale, Sicurezza informatica per modelli di frontiera, Rischi catastrofici / esistenziali
Sara Candussio linkedin.com/in/sara-candussio-830772283?utm_source=share_via&utm_content=profile&utm_medium=member_android github.com/saracandussio saracandussio.github.io/ scholar.google.com/citations?user=ktAv1wgAAAAJ&hl=en	Trieste, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML
Maria Federica Martino Lena	Londra, Regno Unito	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale
Leonhard Waibl linkedin.com/in/leonhard-waibl/	Graz, Austria	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML
Emanuel Marino /	Torino, Italia	AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Alessandro Pisent linkedin.com/in/alessandro-pisent/	Padova, Italia	Robustness e adversarial ML, AI governance e policy, Sicurezza informatica per modelli di frontiera
Luigi Gresele lgresele.github.io/	Copenhagen, Danimarca	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking)
Shelyn Liu shelyn liu in linkeidn	Torino	AI governance e policy, Etica dell'AI e impatto sociale
Margherita Rigato linkedin.com/in/margherita-rigato-184116247?utm_source=share_via&utm_content=profile&utm_medium=member_android	Padova, Italia	Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, AI governance e policy, Sicurezza informatica per modelli di frontiera, Rischi catastrofici / esistenziali
Ilyass Ouardi ouardi-ilyass.github.io/ github.com/OUARDI-ILYASS linkedin.com/in/ilyass-ouardi/	Milano, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, Rischi catastrofici / esistenziali
Daniele Bertillo	Roma, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Diego Doimo	Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment)
Davide Mattei linkedin.com/in/davide-mattei	Rovereto (TN), Italia	AI governance e policy, Etica dell'AI e impatto sociale, Rischi catastrofici / esistenziali
Simone Gargiulo linkedin.com/in/simone-gargiulo-phd-a3a879146	Berkeley, USA	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale
Federico Cavaletto it.linkedin.com/in/fedecava	Torino, Italy	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), Rischi catastrofici / esistenziali
Valerio Lattarulo linkedin.com/in/valerio-lattarulo-2399ab307/?isSelfProfile=true	Milano, Italia	Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Alignment (RLHF, scalable oversight, value alignment), Rischi catastrofici / esistenziali

Want to be part of this list? Join the community and get involved.

Ready to Join Our Community?

Whether you're a researcher, student, professional, or simply curious about AI safety, there's a place for you in our community.

Join the Community