Another testsuite that I’ve used a lot is the much older SVG 1.1 testsuite, which covers SVG animation. GtkSvg passes most of these tests as well, which I am happy about — animation was one of my motivations when going into this work.
2024年12月25日 星期三 新京报
，这一点在下载安装 谷歌浏览器 开启极速安全的 上网之旅。中也有详细论述
Дания захотела отказать в убежище украинцам призывного возраста09:44
Returning back to the Anthropic compiler attempt: one of the steps that the agent failed was the one that was more strongly related to the idea of memorization of what is in the pretraining set: the assembler. With extensive documentation, I can’t see any way Claude Code (and, even more, GPT5.3-codex, which is in my experience, for complex stuff, more capable) could fail at producing a working assembler, since it is quite a mechanical process. This is, I think, in contradiction with the idea that LLMs are memorizing the whole training set and uncompress what they have seen. LLMs can memorize certain over-represented documents and code, but while they can extract such verbatim parts of the code if prompted to do so, they don’t have a copy of everything they saw during the training set, nor they spontaneously emit copies of already seen code, in their normal operation. We mostly ask LLMs to create work that requires assembling different knowledge they possess, and the result is normally something that uses known techniques and patterns, but that is new code, not constituting a copy of some pre-existing code.
I completely ignored Anthropic’s advice and wrote a more elaborate test prompt based on a use case I’m familiar with and therefore can audit the agent’s code quality. In 2021, I wrote a script to scrape YouTube video metadata from videos on a given channel using YouTube’s Data API, but the API is poorly and counterintuitively documented and my Python scripts aren’t great. I subscribe to the SiIvagunner YouTube account which, as a part of the channel’s gimmick (musical swaps with different melodies than the ones expected), posts hundreds of videos per month with nondescript thumbnails and titles, making it nonobvious which videos are the best other than the view counts. The video metadata could be used to surface good videos I missed, so I had a fun idea to test Opus 4.5: