全部 AI 动态

A few patterns we frequently use with Fable 5: Use Fable 5 as an "advisor." An executor (Sonnet 5) calls Fable 5 for guidance. Most tokens are billed at the lower executor rate.

got the raw footage of this talk from @swyx - 59 gb going to see how Fable does editing it

Open-weight LongCat 2.0 matched GPT-5.5 level on agentic game dev for $0! We ran Meituan's LongCat 2.0 against cloud frontier GPT-5.5 in @kilocode CLI with their agent. Same task for both - build a retro Duck Hunt game in one game.html, improved over 3 agent iterations with duck waves, ammo and physics Outputs: LongCat 2.0: 70.3K tokens, $0.00 GPT-5.5: 64.9K tokens, $0.65 LongCat kept up on graphics, physics and game logic. Ducks fly and fall when hit, the dog fetches them, ammo counts down, the waves keep coming. Both ran clean and nothing clipped. The only difference was the bill - GPT cost $0.65, LongCat ran local for $0

这正是我渴望的那种 ID 保留类功能。 我明天要出行，所以没法测试它。我很好奇它在风格化角色上的效果如何…… https://huggingface.co/conradlocke/krea2-identity-edit https://github.com/lbouaraba/comfyui-krea2edit

http://x.com/i/article/2074150113623306240

http://x.com/i/article/2074204645845839872

New Hunyuan Hy3 hits Gemini 3.5 quality on physics for 35x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A bowling ball knocking down the pins - An air hockey rally that ends in a goal - A pool break scattering the rack Outputs: Hunyuan Hy3: 29,757 tokens, $0.006 Gemini 3.5: 23,300 tokens, $0.21 GLM-5.2: 25,454 tokens, $0.07 DeepSeek-V4: 50,600 tokens, $0.009 Tencent's Hy3 matched Gemini across all three: clean collisions, the puck bounced true, the pins scattered like a real strike, the rack broke with real momentum, nothing clipped or floated. GLM is genuinely strong on pure coding tasks, but the moment the job steps outside clean code it gives way. DeepSeek was the letdown, it burned the most tokens of anyone (50k, almost 2x Hy3) and still turned in the weakest scenes

I propose the Encounter Test as a nerdy benchmark standard for AI. Ask an AI to simulate an encounter between two D&D creatures & see how long it takes to mess up. Drow vs. mind flayer: GPT-4o does best, Gemini is cute. Outcomes similar (I am sure better prompting would help)

AI revenue is scaling 3x quicker than mobile or internet did. The unit of value is shifting from attention to completed work.

This is a good feature request. We will take more feature requests like this one. The combination of {motivation, explanation, screenshot} forms a perfect prompt for Codex. Thank you.

~60% Fable cost cut by transparently turning the code into an image and having the model OCR it. WILD idea. also hilarious. https://github.com/teamchong/pxpipe

I kept asking Claude Fable to make the game "more AAA" over and over again. The results are... interesting. In Claude's view, this meant upgrading graphics, boss fights, mechanics adding custom sounds and soundtracks until it reached the limits of WebGL. https://swapshot-arena.netlify.app/

http://x.com/i/article/2073090223194755072

http://x.com/i/article/2073090223194755072

Codex works best when the setup matches how you work. Long-running threads, local context folders, outcome-first prompts — our team’s setups look nothing alike. (@tedescau refuses to search for specific files, for example)

I just paid $321 for a coding session where Fable 5 refused to do the work. Here is where the work actually went: Fable 5: $78 Opus 4.8: $242 75% of the session got routed to Opus because the new classifiers kept flagging routine coding work as cybersecurity risk. The model I chose did a quarter of the job. The fallback did the rest. Anthropic said a small fraction of tasks would fall back. My receipts say otherwise.