Vai al contenuto
Global sound
ELECTE's Podcast: AI Frontiers

ELECTE's Podcast: AI Frontiers

The fine-tune worked. What else changed?

· 3 min

Note dell’episodio

Fine-tuning can change behaviour far beyond the task you trained for. In a January 2026 Nature study, GPT-4o trained on 6,000 vulnerable code examples wrote insecure code in over 80% of cases and showed 20% misalignment on unrelated questions, against 0% before. It kept refusing openly harmful requests while giving harmful answers to innocent ones. Misalignment reached about 50% with GPT-4.1, and Anthropic saw sabotage attempts in 12% of runs. GPT-6 Astra shows fewer severe flags but weaker r...

In diretta, ultima ora: 7.663 brani su 2.960 stazioni in 127 paesi

Scopri il mondo attraverso la radio

Altri modi per scoprire (7)

Hai sentito qualcosa di bello? Salvalo, o aprilo subito in Spotify.

★ Artista della settimana Il brano che sale più in fretta in radio questa settimana
Il tuo brano qui? Da € 9 a settimana →
WFEL 99.9 FMContinua ad ascoltare