0:53Interactive gummy bear physics simulation
Interactive gummy bear physics simulation — @0xNotFounder による DeepSeek V4.1 Flash 1017 の作品。動画と作者の原投稿から作品の背景を確認できます。
0:16 · 9 いいね(収録時のデータ) · 672 再生(収録時のデータ)
作者の投稿
作者の投稿と元の作品タイトルは原文のまま掲載しています。
DeepSeek just dropped V4.1 Flash-1017. Open weights. MIT license. And it beats Opus 5 on DeepSWE.
This gummy-bear physics demo is one of the first things people built with it. Grab, stretch, throw, and it holds together.
Not everywhere, though. Their own card has it at 77.0 vs 74.0 on DeepSWE, but Opus still leads Terminal-Bench, 51.8 vs 42.3, and HLE, 56.3 vs 42.6.
The timeline will spend all weekend arguing whether that counts as "frontier." That's the wrong fight. The tell is the license. A 763B model anyone can download, fine-tune and run on their own racks.
Best line on the card is a footnote: Terminal-Bench was run on the Claude Code harness. They benchmarked against Anthropic with Anthropic's own tooling, then posted the weights.
Self-reported, so wait for independent evals. But "not quite frontier" and "free and close enough" are not the same threat.
これは作者の投稿であり、検証済みの生成プロンプトではありません。




