Post Thumbnail

Artificial intelligence learns to avoid suffering: Google DeepMind Research

Researchers from Google DeepMind and the London School of Economics conducted an unprecedented experiment studying artificial intelligence’s ability to respond to “pain” and “pleasure”. The study involved nine major language models, including ChatGPT and Gemini 1.5 Pro, which demonstrated unexpectedly “human-like” behavior.

In the experiment, AI models were presented with a text-based game offering a choice between two scenarios: obtaining a high score with the risk of “pain” or a low score with guaranteed “pleasure”. The results were striking: artificial intelligence consistently sacrificed high scores to avoid “painful” consequences.

Particularly demonstrative was the behavior of Google’s Gemini 1.5 Pro model, which systematically chose a “pain” avoidance strategy, even when it led to the loss of potentially high results. Moreover, the models demonstrated the ability to adjust their behavior depending on the intensity of the offered stimuli.

“While the results don’t prove consciousness in AI, they lay an important foundation for future research,” notes Jonathan Birch, LSE professor and study co-author. The experiment’s methodology was inspired by similar studies of animal behavior, particularly hermit crabs’ reactions to unpleasant stimuli.

Unlike traditional research based on AI systems’ self-reports, the new approach focuses on behavioral responses without direct questions about artificial intelligence’s internal states. This allows for a more objective picture of AI decision-making processes.

The research raises important questions about ethical and legal aspects of artificial intelligence development, especially in the context of systems demonstrating behavior similar to living beings. As AI evolves, such observations become critically important for developing ethical principles and reassessing artificial intelligence’s role in society.

Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.

Latest News

AI fraudster posed as Keanu Reeves for 2.5 years and stole $160,000

Dianne Ringstaff became a victim of sophisticated fraud when she was playing a mobile game and received a message followed by a video call. Artificial intelligence technologies were so advanced that the woman was absolutely certain — the real Keanu Reeves was calling her.

70-kilogram humanoid flies on turbines

Italian engineers accomplished the incredible. The metallic flying humanoid iRonCub3 with human proportions weighing 70 kg flies! 4 powerful turbines lifted the humanoid to a height of 50 cm, demonstrating technology that previously existed only in science fiction.

MIT and Microsoft exposed GPT-3.5's lies

A team of scientists from MIT and Microsoft developed a methodology that allows looking behind the scenes of language models' thinking. And understanding when they lie to us. The research reveals disturbing cases of systematic mismatch between the real reasons for models' decisions and their verbal explanations.

OpenAI lures Microsoft clients with discounts

OpenAI company began providing significant discounts on ChatGPT corporate subscriptions — from 10 to 20%! But discounts are available with additional investments in other OpenAI products, including Deep Research, Codex and increased API expenses. And this unprecedented move causes serious concern at Microsoft.

GigaChat lost to Claude and Gemini in Russian language on MERA benchmark

Testing GigaChat reveals the harsh truth about Russia's place in the global artificial intelligence race. Recent tests on the MERA benchmark showed results that force serious reflection. The Russian model, created specifically for working with Russian language, unexpectedly lost to foreign competitors in its own "native element".