微信扫码
添加专属顾问
我要投稿
别再被榜单迷惑!实测教你识别编程模型的真实差距。 核心内容: 1. 榜单评分的局限性及优化陷阱 2. AI编程"出新手村"的关键标志 3. 模型互评代码的实用测试方法
好奇个问题,怎么测出来,对sonnet 4.5,有巨大提升?
其实,我好奇的确实是,sonnet 4.5跟 opus的差距不是那么大。从基准测试来说,也是差了3分。
ObjectiveBuild a visually stunning, high-fidelity 3D voxel-style simulation of the Golden Gate Bridge in Three.js.Prioritize complex visuals (not simple blocks), strong atmosphere depth, and smooth ~60FPS.Visuals & Atmosphere- Lighting: a Time-of-day slider (0–24h) that controls sun position, intensity, sky color, and fog tint.- Fog: volumetric-feeling fog using lightweight sprite particles; slider 0–100 (0 = crystal clear, 100 = dense but not pure whiteout).- Water: custom shader for waves + specular reflections; blend horizon with distance-based fog (exp2) so the far water merges naturally.- Post: ACES filmic tone mapping + optimized bloom (night lights glow but keep performance).Scene Details- Bridge: recognizable art-deco towers, main span cables + suspenders, piers/anchors consistent with suspension bridge structure.- Terrain: simple but convincing Marin Headlands + SF side peninsula silhouettes.- Skyline: procedural/instanced city blocks on the SF side to suggest depth.- Traffic: up to ~400 cars via InstancedMesh, properly aligned on the deck (avoid clipping). Headlights/taillights emissive at night.- Ships: a few procedural cargo ships with navigation lights moving across the bay.- Nature: a small flock of animated birds (lightweight flocking).Night ModeAt night, enable city lights, bridge beacons, street lights, vehicle lights, ship nav lights.Tech & Controls (Important)- Output MUST be a single self-contained HTML file (e.g., golden_gate_bridge.html) that runs by opening in Chrome.- No build tools (no Vite/Webpack). Pure HTML + JS.- Import Three.js and addons via CDN using ES Modules + importmap.- UI: nice-looking sliders for Time (0–24), Fog Density (0–100), Traffic Density (0–100), Camera Zoom.- Optimization: use InstancedMesh for repeated items (cars/lights/birds), avoid heavy geometry, keep draw calls low.
这个视频是GPT-5.1-Codex-Max 做的。其实GPT-5.2-Codex和Gemini 3 Pro做得更好,我只是没录视频而已。对了,Gemini 3 Flash做得也比较让人惊喜。
53AI,企业落地大模型首选服务商
产品:场景落地咨询+大模型应用平台+行业解决方案
承诺:免费POC验证,效果达标后再合作。零风险落地应用大模型,已交付160+中大型企业
2026-04-17
Anthropic自己承认了:1M上下文是个伪命题,上下文的锅得自己背!
2026-04-17
Claude 4.7 正式发布!更强但中国用户更难
2026-04-17
赛博鸡生蛋,7小时用Claude Vibe Coding一个Mini-Claude
2026-04-17
Claude Opus 4.7 发布,全网最详细解读
2026-04-16
claude opus 4.7,来了!不过Token 消耗可能更贵了
2026-04-16
Anthropic放出Opus4.7,附最新使用方法!
2026-04-16
Anthropic新旗舰Opus 4.7:代码能力远超GPT-5.4,文档推理全场第一,今天可用
2026-04-16
Google官宣:AI写代码成功率从28%飙到96%!秘密武器竟是一个文件夹
2026-01-24
2026-04-15
2026-01-23
2026-01-26
2026-03-31
2026-03-13
2026-01-21
2026-02-14
2026-02-03
2026-02-03