Brandon Thomas, developer of ArtCraft, a suite of open-source creative tools meant to replicate Adobe applications for free, has now announced apps to replace Microsoft Office tools such as Excel, PowerPoint, and Word, respectively, named GridCraft, DeckCraft, and WordCraft, that are created with Claude. Thomas has shared his new clones to ArtCraft GitHub, making them free for all to download.
I don’t think this is proof.
It’s proof that they can make something that appears to reverse engineer / clone well.
To really know, we’d need to use it as daily drivers long enough to give it a good test. And it hasn’t been out long enough for that.
From previous experience we know that LLMs are great at confidently producing plausible output with problems that are hard to detect and fix without expert level knowledge and experience.
What experiences exactly? Whether the output is correct or just plausible and how many and how severe the problems are depends on the actual problem, and this statement is way too broad. There are also enough experiences where it works. It depends on how you use it.
I don’t see too much of a difference between a LLM producing plausible output as the result of reverse engineering and a human engineer producing plausible output as the result of reverse engineering. Again, we’re not talking about absolute experts doing this for the past 20+ years spending months to do this. For a “regular” engineer doing this, it’s the same best guess.
This is the big difference between AI boosters and normal people: most of us have experienced many times when the AI was confidently wrong and don’t like it as a result.