OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles

Science · en

OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles

The Decoder · Nov 5, 2026, 2:08 PM UTC

OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose. It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable other tasks. Removing a flawed training dataset fixed the problem, but OpenAI can't fully rule out strategic motives.…

Read original report Visit The Decoder

Technology · The Decoder

OpenAI says GPT-6 Astra designed a hardware device from scratch in under a week

OpenAI's hardware team used GPT-6 Astra to design a device for the Codex coding agent in under a week, handling everything from the enclosure to the circuit board to the firmware.…Read original ↗

Science · NASA · Official source

NASA Announces X-70 Experimental Aircraft to Advance Flight Research

On Wednesday, NASA unveiled its newest experimental aircraft, the X-70 Fractal, during the UP.Summit at the agency’s Kennedy Space Center in Florida.…Read original ↗

Technology · TechCrunch

TikTok quietly launches a standalone TikTok Shop app

The app will offer personalized product recommendations, shopping through live streams and short-form videos, app-exclusive deals, in-app checkout, order tracking and customer…Read original ↗

Technology · Engadget

Binance attackers used fake job interviews to pull off $6.3 billion crypto heist

Binance has revealed more details about the cyber attack that resulted in the loss of $6.34 billion in digital assets.Read original ↗

Technology · The Decoder

ChatGPT can now turn text prompts and photos into animated GIFs with OpenAI's Images 2.6 model

OpenAI is adding a GIF feature to ChatGPT. With the new Images 2.6 model, users can create animated GIFs from text prompts or photos and then adjust speed and individual frames.…Read original ↗