Watch astronaut Christina Koch and Google’s James Manyika discuss space, technology, and discovery.
Christina Koch sits down with James Manyika, Google’s Senior Vice President of Research, Labs, Technology & Society.
en
637
66
Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdependent decisions. We introduce Stellar Colosseum, a model-agnostic harness for allocating inference across research in mathematics and theoretical computer science. Colosseum explores alternative strategies before proof construction, uses a readiness gate to decide when a route is mature enough to decompose, represents the proof plan as interdependent section-level subproblems, and routes verifier findings back to the affected part of the argument. Across these stages, it generates candidates in parallel, attacks them with targeted falsification, and combines candidates and their critiques into a single research artifact through overlapping random-sample tree aggregation. The Colosseum workflow has also been integrated into Google Antigravity's Teamwork framework as the Long Proof pattern. We demonstrate the capabilities of Colosseum through open-ended research and evaluations on theorem-proving and competitive programming benchmarks. Using Colosseum with Gemini 3.1 Pro, we obtain several new results that address open problems arising from papers published at top venues such as FOCS and JMLR. On TCS-Bench, a benchmark of research-level theorem-proving tasks drawn from papers published at FOCS, STOC, and SODA, Colosseum achieves 71.0% accuracy using Gemini 3.1 Pro and Gemini 3.7 Flash. In a separate Codeforces evaluation using Gemini 3.1 Pro, the proof-oriented pipeline with execution feedback solves 218 of 222 problems.
en
Before You Poll with LLMs: A Deliberative Diagnostic Framework
Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM personas simulate public opinion at scale. Current evaluations test only whether personas hold the right opinions -- a static snapshot. But opinion research increasingly depends on dynamic fidelity: whether personas update beliefs in response to new arguments, as humans do during deliberation. No existing benchmark tests this. We introduce the Deliberative Polling Diagnostic Framework, which compares human and LLM belief shifts after identical informational interventions. Grounded in deliberative polling, it surfaces failures invisible to static evaluation: models that produce plausible partisan opinions can still misrepresent how those opinions change. Applying the framework to five frontier models using data from America in One Room (526 personas, 72 questions), we find that every model fails, each in a unique manner. GPT-5.1 exhibits reversal: its personas become more hostile toward the opposing party after balanced information, while humans become less so. This reversal is selective (80% on outgroup vs. 26% on policy questions) and symmetric across partisan identities. Gemini 2.0 Flash, Claude Sonnet 4.5, and Llama 3.3 70B exhibit overshoot, shifting correctly but at 5-7x human magnitude. DeepSeek V3 exhibits rigidity with near-zero change. Targeted ablations reveal that policy content triggers these failures and that they are identity-specific: GPT-5.1 reverses on outgroup questions but overshoots on ingroup; Gemini shows the inverse. We term this signature self-sycophancy: conformity to the model's internal stereotype of the persona rather than reasoning from the information provided. Our framework offers a concrete protocol: run the deliberative diagnostic before trusting LLM personas to mimic revised beliefs.
en
DevFest is back
Animation of the text "{DevFest} 2026 Join us! Google Developer Groups" with a globe icon, asterisk icon, < icon, and > icon
en
Perplexity Portable Computer Is Now Available on Windows, Powered by NVIDIA RTX
As local models become more capable, AI agents can handle more work directly on a PC while keeping sensitive information on the device. Portable Computer is a local version of the agent Perplexity Computer that plans and carries out multistep tasks. Accelerated by NVIDIA GPUs, it uses local models to analyze data, bring together information […]
en
Slack can now vibe-code interactive charts and reports inside chats
A new feature coming to Slack will allow you to build interactive reports, polls, dashboards, presentations, microsites, and other tools directly inside a chat. With…
en
3 ways to prep for your next big race with Search
Illustration on a blue background of technicolor runners with a magnifying glass and Gemini spark overlaid
en
Why the current tech backlash feels different
This interview has been lightly edited for length and clarity. Nick Statt: Hello and welcome to Decoder, Nilay’s show about big ideas and other problems.…
en
Recreating a 70-year love story frame by frame
An elderly couple sitting in a movie theater. Overlayed are "Teulluride Film Festival" and "Love, Rendered"
en
Get ready for the game with new football features in Search
An illustrated graphic set against a vibrant green background featuring American football elements, including a gold trophy, a blue helmet, a silver whistle, a football, a mini scoreboard, and play diagrams, with the icon for AI Mode in Google Search in t
en
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning
Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally intensive and opaque. We demonstrate that a pure Large Language Model (LLM), when equipped with specialized modules, can rival state-of-the-art LMMs on complex geometry problems. Our framework integrates a Geometric Vision Parser, which translates diagrams into symbolic form, with a Symbolic Solver that performs formal deductions, thereby mitigating hallucinations and promoting interpretable reasoning. To enable rigorous evaluation, we curate a benchmark of challenging problems from the 2025 Chinese Zhongkao examinations, ensuring data novelty and testing deeper deductive skills. Experiments demonstrate that our approach achieves performance comparable to Gemini 2.5 Pro while delivering clearer, human-like solutions.
en