Season's Savings | ₹5/mo for 3 months

₹199/month after first 3 months. Renews automatically. Terms apply.
The fine-tune worked. What else changed? cover art

The fine-tune worked. What else changed?

The fine-tune worked. What else changed?

Listen for free

View show details
About this listen
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 reasoning monitoring. Why task tests and refusal tests are not enough.

Send us a text.

AI Frontiers is produced by ELECTE, the AI-powered analytics platform for European SMEs.

The AI analysis 100,000+ readers trust. Join them:

- Subscribe to the ELECTE newsletter

- Official Merch


Written and hosted by Fabio Lauria.

adbl_web_anon_alc_button_suppression_t1
No reviews yet