Recently updated channels

Pick one to see only that channelBrowse all channels →

Results

10 articles
Sort
4 slides11:31EN
Matthew Berman· Jan 29, 2026Exploring Google’s Project Genie: Interactive Worlds with Genie 3AlexAlex tests generated racetracks, alien structures and cloud landscapes, showing both the prototype’s creative options and its control limitations.World modelsGenerative mediaVision & video+2
4 slides10:50EN
Matthew Berman· Sep 30, 2025Sora 2: Generated Video, Sound and Cameos in an Early DemonstrationMatthew Berman · Forward FutureMatthew Berman reviews launch examples and tries the early web and mobile experience, noting both visual realism and artifacts.Generative mediaVision & videoWorld models+1
6 slides17:03EN
Matthew Berman· Mar 28, 2025Matthew Berman Explores GPT-4o Image Generation and Its LimitsMatthew Berman · Forward FutureFrom animated trailer remakes to infographics and interface mockups, early examples show creative possibilities alongside persistent errors.Generative mediaVision & videoCreativity+2
3 slides14:23EN
Matthew Berman· Dec 9, 2024Sora’s Initial Release: Storyboards, Remix and a Launch-Day TestMatthew Berman · Forward FutureMatthew Berman explores the 2024 video generator’s editing tools and reports mixed results from his first attempts.Generative mediaVision & videoProduct & UX
4 slides11:14EN
Matthew Berman· Sep 18, 2024Pixtral 12B: Testing a 2024 Vision-Language ModelMatthew Berman · Forward FutureMatthew Berman runs informal image, text and interface-generation tests of Mistral’s Pixtral on a sponsor-provided cloud GPU.Multimodal AIVision & videoOpen-weight models+1
5 slides12:17EN
Matthew Berman· Aug 7, 2024Testing Gemini 1.5 Pro on Code, Reasoning, Images and VideoMatthew Berman · Forward FutureMatthew Berman compares standard and experimental Gemini versions in an informal 2024 review, finding mixed results and repeated output errors.GeminiEvalsMultimodal AI+2
3 slides13:37EN
Matthew Berman· May 16, 2024Testing Gemini 1.5 Pro’s Long Context and Video UnderstandingMatthew Berman · Forward FutureMatthew Berman’s 2024 tests show useful image and video summaries alongside blocked code and missed details.Multimodal AIBenchmarksVision & video+1
5 slides14:12EN
Matthew Berman· Mar 26, 2024Matthew Berman Reviews Sora’s Early Filmmaker ExperimentsMatthew Berman · Forward FutureA look at early Sora-generated films, surreal creatures and the questions they raise about creative work, compute and video simulation.Generative mediaVision & videoCreativity+2
7 slides16:27EN
Matthew Berman· Feb 29, 2024Matthew Berman Reviews EMO’s Audio-Driven Portrait Video ResearchMatthew Berman, Jensen Huang · Forward FutureAlibaba researchers animate a portrait from an image and vocal audio; Berman examines the method, its limitations and the implications for trust in video.Generative mediaVision & videoDeep Learning+1
Slides6:57EN
Matthew Berman· Nov 22, 2023A Camera Narrator Using GPT-4 Vision and ElevenLabsMatthew Berman · Forward FutureMatthew Berman demonstrates a 2023 project that turns webcam frames into spoken nature-documentary-style narration.Voice AIMultimodal AIVision & video