←DeepMind
← All topics

DeepMind

English text is being prepared.

Public reading groups
31
Last 30 days
18
Directory status
Legacy topic

LatestAMD Acquires World Labs for $8.2 Billion; Fei-Fei Li to Serve as AMD Executive Vice President and Chief Scientist

Latest reading groups

Duplicate reports of the same fact are grouped

  1. Leiphone
    AI score80

    AMD Acquires World Labs for $8.2 Billion; Fei-Fei Li to Serve as AMD Executive Vice President and Chief Scientist

    AMD announced an all-stock acquisition of World Labs, founded by Fei-Fei Li, for approximately $8.2 billion. After the deal closes, Fei-Fei Li will serve as AMD Executive Vice President and Chief Scientist, reporting directly to Lisa Su, and World Labs' roughly 70-person team will be integrated as a relatively independent research unit. The article reviews Fei-Fei Li's three directional choices—from ImageNet, to AI democratization, to spatial intelligence—and notes that this acquisition is about 52% higher than World Labs' $5.4 billion valuation after its February 2026 Series C funding round. The author believes that what comes next is whether the performance gains of Atlas and Marble on MI450 can continue the curve of the 4x speedup on MI325X, and whether other spatial intelligence teams will consequently shift to AMD hardware.

    Why read thisThe article reviews Fei-Fei Li's three directional choices from ImageNet to World Labs, and lays out two concrete criteria for judging whether spatial intelligence succeeds following the AMD acquisition.

  2. QbitAIModel releases
    AI score81

    Google Releases Gemini 4 Carbon, Surpassing Claude Opus 5.5 on Multiple Benchmarks

    Google has released its new flagship model Gemini 4 Carbon, which tops the Artificial Analysis Intelligence Index 5.0 with a score of 59, surpassing Claude Opus 5.5 and GPT-6 Astra. It scored 65.2% on Terminal-Bench 4.0, 96.2% on GraphWalks for 256k to 1M context, and 88.2% on SEC-bench Pro vulnerability discovery. Initial pricing is $2 per million tokens for input and $10 per million tokens for output, with cached input as low as $0.2; because of its vulnerability discovery and exploitation capabilities, it will first be made available to select cybersecurity defenders.

    Why read thisThe original text lists Carbon's specific scores and pricing on terminal coding, long-context, and safety benchmarks, allowing comparison with Opus 5.5 to gauge the gap.

  3. ArenaAnalysis
    AI score70

    Gemini 4 Carbon ranks 2nd on Agent Arena with a net improvement of 16.2%

    Arena.ai says Gemini 4 Carbon ranks 2nd in the real-task-based Agent Arena with a net improvement of 16.2%, and sits on the Pareto frontier for cost, time, and output tokens per task. Compared with Gemini 4 Argon, which ranks 7th with an 11% improvement, Carbon is 5 places higher and 5.2 percentage points better; the gains mainly come from a +13.2 percentage point increase in the positive-feedback-to-complaint ratio, +5.6 percentage points in confirmed success, and +4.8 percentage points in steerability. Arena says Carbon's availability will be announced by Google DeepMind.

    Why read thisArena's empirical data breaks down Carbon's improvement over Argon into three signals—steerability, task completion rate, and user sentiment—making it easier to identify the source of the gap.

  1. Google BlogFirst-partyModel releases
    AI score78

    Google DeepMind releases world model Genie 4, supporting real-time interactive simulation and native audio

    Google DeepMind releases the world model Genie 4, focused on real-time interactive simulation and introducing native audio for the first time in the series. The model is built on capabilities from the Gemini family: Gemini Omni is responsible for making simulations match the appearance and behavior of the real world, while other Gemini models provide the complex reasoning needed to maintain simulation coherence. Users can control scenes in real time using natural language, such as moving the camera, changing the weather, or introducing new characters, and each world also generates ambient sound, music, and interactive dialogue on the fly.

    Why read thisThe original text explains that Genie 4 adds native audio and natural language control to real-time interactive simulation, allowing readers to understand the new capability boundaries of world models.

  1. 36Kr · AIResearch
    AI score81

    DeepMind paper points out rounding bugs in Softmax and cross-entropy implementations; Gemini participated in discovery and fix

    Jon Barron, a principal research scientist at Google DeepMind, disclosed that the standard implementations of Softmax and cross-entropy in PyTorch, JAX, and textbooks contain two floating-point rounding bugs, which cause gradients to be zeroed out and ghost gradients to appear in distillation. The team submitted the paper "Fixing Softmax and Cross-Entropy" to arXiv, giving a rewrite solution; in the modular addition (a + b mod 31) task, test accuracy under bfloat16 precision increased from 93.3% to 100.0%. Barron said the bug was initially discovered and fixed by Gemini Flash 3.7, most of the paper's experiments were completed by Flash 3.8, and Gemini 4 Argon wrote the first draft.

    Why read thisThe original text sorts out the causes of two floating-point rounding defects in Softmax and cross-entropy implementations, and provides accuracy comparisons before and after the fix.

  1. Alex Heath
    AI score65

    Pichai responds to Hassabis stepping down as DeepMind head and Jeff Dean leaving Google

    Alex Heath relays Sundar Pichai's explanation for Demis Hassabis stepping down as head of DeepMind and Jeff Dean leaving Google. Pichai called it a natural evolution after the individuals' long-term commitment, and mentioned that Jeff Dean will go work on Discovery Loop; he said frontier model development has become high-intensity, large-scale work spanning data, compute, algorithms, and team management, while Hassabis wants to devote more time to safely advancing the frontier and using AGI to solve other problems, with AlphaFold and Isomorphic as examples of such applications.

    Why read thisPichai framed the changes involving the two key figures as a natural division of labor after frontier model development became a high-intensity, full-time job.

  1. The PaperResearch
    AI score80

    Four Gemini agents autonomously complete Minecraft, defeating the Ender Dragon in 27 hours

    Four autonomous agents running Gemini 4 Argon took 27 hours and 14 minutes to defeat the Ender Dragon in Minecraft survival mode, with no human intervention throughout and without receiving game-specific training; the DeepMind research team disclosed this experiment in an arXiv paper. During the process, the agents wrote and ran 2,783 programs, exchanged 229 chat messages, died 605 times, processed about 1.35 billion input tokens, and cost about $520 at discounted prices. The paper states this is the first end-to-end autonomous completion using only the standard Mineflayer library, without pre-exploring seeds or human-written game-specific tools.

    Why read thisThe paper discloses that four general-purpose agents autonomously completed the game without game-specific training, comparable to the specialized training approaches of AlphaGo and AlphaStar.

  1. SenseTimeResearch
    AI score78

    SenseTime Releases Empirical Study on GPT-6-Astra Embodied Intelligence and the SenseNova-RoboRSI Framework

    SenseTime has released an empirical study on GPT-6-Astra's embodied intelligence, covering 12 simulation benchmarks and 8 real robot platforms, and has simultaneously open-sourced the SenseNova-RoboRSI framework and a 27B model whose operating cost is about 1/50 that of GPT-6-Astra. Under a unified protocol (ICL plus up to 10x interaction budget), GPT-6-Astra achieved SOTA on all 12 benchmarks: RoboDojo rose from 27.6% at 1x budget to 81.9% at 10x, DexJoCo reached 87.3% versus the previous SOTA of 40.3%, and the LIBERO benchmark was pushed to saturation. The study also notes that the inference cost for simple tasks such as putting a pen into a pen holder is about $55, and that real robots overheat and wait times are too long; the conclusion is therefore that GPT-6-Astra has largely crossed the threshold of embodied capability, but practical-grade embodied intelligence has not yet arrived.

    Why read thisSenseTime tested GPT-6-Astra across 12 simulation benchmarks and 8 real-robot platforms, and identified concrete gaps in cost and real-time performance.

  1. 36Kr · AIResearch
    AI score76

    DeepMind AlphaProof Nexus appears in《Science》: autonomously solves 9 Erdős problems

    Google DeepMind's automated mathematical proof system AlphaProof Nexus appeared in the October 8 issue of《Science》, autonomously solving 9 of 353 open Erdős problems, two of which had remained open since 1970. The system uses Gemini 3.1 Pro to draft proofs in Lean, with a compiler verifying line by line and feeding back iterations; the reasoning cost per problem is several hundred dollars. The paper's ablation results show that a simplified system that removes complex structures such as the sub-agent tournament and retains only the large model plus Lean feedback can also solve these 9 problems, though the hardest few are more expensive.

    Why read thisThe paper discloses the solve rate, cost, and ablation results on 353 Erdős problems, allowing readers to judge the true capability boundary of the formal proof system.

  2. François Chollet
    AI score73

    Chollet: Gemini 4 Argon performs comparably to Astra on ARC-AGI-3, Google returns to the frontier

    François Chollet stated that Gemini 4 Argon's performance on ARC-AGI-3 is close to Astra's, and Google has returned to the frontier. Data cited by ARC Prize shows that Google DeepMind's Gemini 4 Argon achieved 97.5% (provider adapter harness, $4.8K) and 49.8% (standard harness, $5.8K) on ARC-AGI-3, 91.3% at $0.32/task on ARC-AGI-2, and 98.5% at $0.16/task on ARC-AGI-1, making it the second frontier AI lab to exceed 95% on ARC-AGI-3.

    Why read thisA second lab to break 95% on ARC-AGI-3 has emerged, and readers can use this to observe where frontier models stand in competition on this benchmark.

  5. ARC PrizeFirst-partyAnalysis
    AI score81

    ARC Prize announces evaluation results of Gemini 4 Argon on the ARC-AGI series

    ARC Prize announces the validated results of Google Gemini 4 Argon on ARC-AGI: ARC-AGI-3 reaches 97.5% (provider adapter harness, cost $4.8K), and 49.8% under the standard harness (cost $5.8K); ARC-AGI-2 is 91.3%, at $0.32 per task; ARC-AGI-1 is 98.5%, at $0.16 per task. ARC Prize states that Google DeepMind is the second frontier AI lab to exceed 95% on ARC-AGI-3, and Argon's 97.5% is second only to GPT-6 Astra's 99.9%. The standard harness test failed to complete all 55 games due to API issues, and the high reasoning tier completed only 19 games so no score was published; costs are calculated at the current discounted price of $2 per million input tokens and $10 per million output tokens.

    Why read thisARC Prize announces the scores and per-task costs of Gemini 4 Argon on the three generations of ARC-AGI benchmarks, allowing comparison of performance differences under different harnesses.

  1. ZhidongxiModel releases
    AI score86

    Google DeepMind launches general physical reasoning model Gemini 4 Argon

    Google DeepMind officially launched the general physical reasoning model Gemini 4 Argon and released a demo video of its collaboration with the Apptronik Apollo humanoid robot. The robot only watched a video demonstrating beanbag tossing, practiced repeatedly, and ultimately made 7 consecutive successful throws. The model possesses visual semantic reasoning, physical understanding, and code generation capabilities, and can be used for robot control, simulation environment construction, physical data analysis, and motion optimization. In pure reasoning mode, it scored 87% on the ERQA benchmark. The demo also covers generating MuJoCo simulation environments from robot-perspective videos, human-perspective videos, and hand-drawn sketches, as well as using simulation data to raise the real robot's grasping success rate from 56% to 75%.

    Why read thisThe demo covers simulation environment construction, zero-shot control, and data generation, showing the specific division of labor of the physical reasoning model in the robot R&D pipeline.