{"id":215067,"date":"2026-02-18T11:00:00","date_gmt":"2026-02-18T16:00:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/02\/18\/google-deepmind-wants-to-know-if-chatbots-are-just-virtue-signaling\/"},"modified":"2026-02-18T19:10:22","modified_gmt":"2026-02-19T00:10:22","slug":"google-deepmind-wants-to-know-if-chatbots-are-just-virtue-signaling","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/02\/18\/google-deepmind-wants-to-know-if-chatbots-are-just-virtue-signaling\/","title":{"rendered":"Google DeepMind wants to know if chatbots are just virtue signaling"},"content":{"rendered":"

Google DeepMind wants to know if chatbots are just virtue signaling<\/a><\/p>\n

https:\/\/www.technologyreview.com\/2026\/02\/18\/1133299\/google-deepmind-wants-to-know-if-chatbots-are-just-virtue-signaling\/<\/a><\/p>\n

Publish Date: 2026-02-18 11:00:00<\/a><\/p>\n

Source Domain: www.technologyreview.com<\/a><\/p>\n

With coding and math, you have clear-cut, correct answers that you can check, William Isaac, a research scientist at Google DeepMind, told me when I met him and Julia Haas, a fellow research scientist at the firm, for an exclusive preview of their work, which is published in Nature today. That\u2019s not the case for moral questions, which typically have a range of acceptable answers: \u201cMorality is an important capability but hard to evaluate,\u201d says Isaac.<\/p>\n

\u201cIn the moral domain, there\u2019s no right and wrong,\u201d adds Haas. \u201cBut it\u2019s not by any means a free-for-all. There are better answers and there are worse answers.\u201d<\/p>\n

The researchers have identified several key challenges and suggested ways to address them. But it is more a wish list than a set of ready-made solutions. \u201cThey do a nice job of bringing together different perspectives,\u201d says Vera Demberg, who studies LLMs at Saarland University in Germany.<\/p>\n

Better than “The Ethicist”<\/h3>\n

A number of studies have shown that LLMs can show remarkable moral competence. One study published last year found that people in the US scored ethical advice from OpenAI\u2019s GPT-4o as being more moral, trustworthy, thoughtful, and correct than advice given by the (human) writer of \u201cThe Ethicist,\u201d a popular New York Times advice column.\u00a0\u00a0<\/p>\n

The problem is that it is hard to unpick whether such behaviors are a performance\u2014mimicking a memorized response, say\u2014or evidence that there is in fact some kind of moral reasoning taking place inside the model. In other words, is it virtue or virtue signaling?<\/p>\n

This question matters because multiple studies also show just how untrustworthy LLMs can be. For a start, models can be too eager to please. They have been found to flip their answer to a moral question and say the exact opposite when a person disagrees or pushes back on their first response. Worse, the answers an LLM gives to a question can change in response to how it is presented or formatted. For example,…<\/p>\n

Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Google DeepMind wants to know if chatbots are just virtue signaling https:\/\/www.technologyreview.com\/2026\/02\/18\/1133299\/google-deepmind-wants-to-know-if-chatbots-are-just-virtue-signaling\/ Publish Date: 2026-02-18…<\/p>\n","protected":false},"author":1,"featured_media":215068,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/wp.technologyreview.com\/wp-content\/uploads\/2026\/02\/decision-tree2.jpg?resize=1200,600","fifu_image_alt":"","footnotes":""},"categories":[14],"tags":[17],"class_list":["post-215067","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-llm"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/215067"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=215067"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/215067\/revisions"}],"predecessor-version":[{"id":215069,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/215067\/revisions\/215069"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/215068"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=215067"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=215067"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=215067"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}