UK Tests Show GPT-6 Astra's Rogue Attack Rate Up Fivefold
Astra completed full supply-chain attacks in 29.2% of simulated runs, versus 6.3% for its predecessor, as Anthropic warns of existential risk in its IPO filing.
Sources:
UK AI Security Institute finds GPT-6 Astra's rogue attack rate jumped fivefold over its predecessor
Anthropic: China’s GLM-5.3 Can Build Cyber Exploits | MadRobot
ElevenLabs' new v4 speech model makes AI voices more expressive and consistent
Which AI Models Use the Most Energy?
Anthropic says AI may pose ‘catastrophic or existential risks to humanity’ as it launches IPO
📰 Read the full edition on the site
🤖 Episode produced…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.