{"id":1183388,"date":"2026-09-03T00:48:23","date_gmt":"2026-09-03T00:48:23","guid":{"rendered":"https:\/\/www.europesays.com\/uk\/1183388\/"},"modified":"2026-09-03T00:48:23","modified_gmt":"2026-09-03T00:48:23","slug":"these-russian-mathematicians-taught-ai-models-how-to-talk-to-each-other-without-using-words","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/uk\/1183388\/","title":{"rendered":"These Russian Mathematicians Taught AI Models How to Talk to Each Other Without Using Words"},"content":{"rendered":"

I recently met with some brilliant Russian mathematicians who showed me a way for artificial intelligence<\/a> models to communicate via something akin to machine telepathy.<\/p>\n

The mathematicians work for a startup<\/a> called Mostik\u2014the Russian word for bridge. It\u2019s a nod to the group\u2019s approach, which allows different models to interact using the mathematical values found in their weights<\/a>\u2014the things that determine how a prompt gets turned into an output. In practice, this means the capabilities of a larger model can be fed to a smaller model to ramp up its intelligence much more efficiently.<\/p>\n

The startup used the approach to build a model that has rocketed to the top of ARC-AGI<\/a> 3, a notoriously difficult competition for AI models. (They wouldn\u2019t tell me more because they want to win the contest.) To demonstrate the idea, however, they also created a bridge between two Chinese open-weight models: the largest version of GLM-5.2, which has 753 billion parameters; and a 4-billion-parameter version of Qwen-3.5<\/a> that can run on a mobile device. The resulting hybrid system costs one-twentieth of the full GLM model, and its performance is exactly halfway between the two.<\/p>\n

\u201cIt\u2019s well-known in machine learning that ensembles of models perform better than individual ones,\u201d Sasha Malysheva, Mostik\u2019s CEO, told me over coffee.<\/p>\n

Malysheva, who developed the approach, shared a running joke inside the company: The future of AI is similar to guessing the weight of a pig. In math circles, it\u2019s well-known that a handful of random people can more accurately estimate a pig\u2019s weight than an expert when their guesses are combined and averaged.<\/p>\n

Much like communally eyeballing porcine heft, combining the outputs of several AI models often nets better results. Typically, this involves feeding the output of one model into another, which takes a good chunk of time and money. The Mostik team, however, figured out a way for AI models to talk to one another without producing text output. If it takes off, it could increase the value of open-weight models, allowing them to better compete with the closed, proprietary models offered by frontier labs like Anthropic<\/a> and OpenAI<\/a>.<\/p>\n

Malysheva says that combining lots of different models may turn out to be a better way to advance AI. \u201cI personally do not think we will have a monolithic model [in the future] or that the capabilities of models will come from scaling,\u201d she told me, referring to the strategy of making models larger and feeding them more data.<\/p>\n

\u201cIf Mostik makes it possible to pair frontier models with domain-specific models\u2014think biology, physics, and so on\u2014many more specialized models would be trained,\u201d says Vladimir Arustamian, the tech lead at the AI software company Lovable, who knows the Mostik team. \u201cThis team has been at it for a matter of months and already has something running that I would have guessed was years out.\u201d<\/p>\n

The Mostik technique means \u201cyou can approach large-model quality without the large model handling the entire loop, giving you substantial improvements with just a smaller model running alongside,\u201d says Karl Tuyls, a former computer scientist at Google DeepMind who is familiar with the company\u2019s tech. The method is a no-brainer for anyone tasked with running models as efficiently as possible, Tuyls says.<\/p>\n

Stanislav Smirnov, a professor at the University of Geneva and a 2010 Fields Medalist, is Mostik\u2019s chief scientist. He says finding common ground between two AI models is surprisingly difficult. “There seems to be no appropriate mathematical language yet,” he says. In the interim, Mostik\u2019s approach is a way to quite literally bridge the gap.<\/p>\n","protected":false},"excerpt":{"rendered":"I recently met with some brilliant Russian mathematicians who showed me a way for artificial intelligence models to…\n","protected":false},"author":2,"featured_media":1183389,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_share_on_mastodon":"0"},"categories":[3163],"tags":[323,193982,28396,1942,128028,20262,10733,1318,53,16,15],"class_list":["post-1183388","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-ai-lab","tag-anthropic","tag-artificial-intelligence","tag-mathematics","tag-neural-networks","tag-open-source","tag-openai","tag-technology","tag-uk","tag-united-kingdom"],"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@uk\/117204360036786572","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/1183388","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/comments?post=1183388"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/1183388\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media\/1183389"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media?parent=1183388"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/categories?post=1183388"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/tags?post=1183388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}