What Matthew Berman’s Team Built With Sonnet 5.5

A short showcase presents an ocean simulation, game prototypes, city rendering and a LEGO design tool.

MBMatthew BermanSpeaker · Forward Future
Channel
Matthew Berman
Published
Sep 29, 2026
Video
1:14
Read
1 min
Slides
2
Original
English
Open on YouTube
Scroll to read and the video shrinks to the bottom-right corner. Captions follow your reading language.
Reading languageAvailable in 2 languages
You're reading the original English.
SUMMARY

In 30 seconds

Matthew Berman shows projects he says his team created with Sonnet 5.5 over a few days. The examples range from a configurable ocean and playable game prototypes to a LEGO creator and a rendered city.

  1. 1Ocean simulationThe demo offers controls over waves, light, wind and a boat.
  2. 2Game prototypesBerman shows a Fall Guys-style game and later describes an Age of Empires-style multiplayer prototype.
  3. 3LEGO creatorThe showcased tool is described as generating designs and step-by-step building instructions.

Takeaways

  1. The showcase includes a 3D ocean with controls for waves, lighting, a boat and wind.
  2. Berman describes game prototypes and a LEGO design tool with assembly instructions.
  3. The short video presents selected demonstrations rather than an independent evaluation of development effort or completeness.
FULL TEXT

Read the edited text by chapter

Transcript only
01

A rapid project showcase

Berman presents several 3D and game projects made with Sonnet 5.5. He describes their features and the team’s short development period.

Ocean simulator
SLIDE 1 / 2Ocean simulatorThe showcase displays a 3D ocean scene with a boat and changing light.

My team and I built several projects over a few days using Sonnet 5.5. One is a 3D ocean simulator with controls for waves, light, a boat and wind. Another is a playable Fall Guys-style game that I describe as having 60 levels and customization from a single prompt.

Fall Guys-style game
SLIDE 2 / 2Fall Guys-style gameA playable obstacle-course prototype appears in the demonstration.

The showcase also includes an Unreal Engine rendering of San Francisco with buildings, people and cars. A LEGO creator accepts a description and produces a design with real pieces and step-by-step instructions. These are examples shown in the video; their completeness is not independently tested here.

I also show an Age of Empires-style multiplayer game and a Batman: Arkham City-inspired recreation. I am excited by what the team could build in a day or two and imagine what a longer development period could produce. The examples illustrate rapid prototyping, though they do not establish that all 3D development problems are solved.

More from this channel

6 slides25:50EN
MBMatthew Berman· Oct 24, 2026Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.Open-weight modelsBenchmarksAI cost & performance+1
2 slides32:20EN
MBMatthew Berman· Oct 23, 2026Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.Local inferenceOpen-weight modelsAI cost & performance+1
45:08EN
MBMatthew Berman· Oct 21, 2026Sam Altman on AI Discovery, Consciousness, Compute and a Human-Centered FutureMatthew Berman, Sam Altman · Forward FutureIn a conversation with Matthew Berman, Altman discusses scientific progress, personal assistants, recursive self-improvement and the importance of human agency.AI for sciencePersonal agentsConsciousness+2
5 slides12:14EN
MBMatthew Berman· Oct 14, 2026Gemini 4 Argon Tested: 3D Demos, a Spreadsheet Prototype and Benchmark ResultsMatthew Berman · Forward FutureMatthew Berman tests Google’s model on games and visual projects, then compares reported coding and agent benchmarks.GeminiBenchmarksCoding agents+1
5 slides10:36EN
MBMatthew Berman· Oct 13, 2026Meta Muse Wonder Tested: Strong Benchmarks, Mixed Demos and Quota FrictionMatthew Berman · Forward FutureMatthew Berman tests Meta’s models on browser demos and reviews their published benchmark scores, availability and cost.Models & trainingBenchmarksAI cost & performance+1
2 slides17:37EN
MBMatthew Berman· Oct 10, 2026AI Coding, Game Mashups and the Value of Human TasteMatthew Berman · Forward FutureMatthew Berman explains decompilation and game mashups, then argues that iterative AI coding changes software and creativity.Coding agentsSoftware engineeringCreativity+1