laurentlb

Watermarking seems feasible for creative tasks (that admit many valid results).

But if I craft a prompt that doesn't leave space for creativity, how can they include a watermark? e.g. "Rewrite the following text, replacing 'foo' with 'bar'."

I'm curious to see where they draw the line, and whether the watermarking really affects the (perceived) quality of results.

Thanks for providing the query and a link to execute it (I didn't know about that one). Now I can play with it and find the most popular words...

"to", "the", "of". I don't know what I expected.

Note that it's also possible to review changes afterwards. Many (human) teams have been working like this.

I agree that many vibe-coders are likely to skip reviews completely, but it doesn't have to be like this.

I've worked 12 years at Google. When I was tech lead, I periodically checked Memegen and searched for my project name. I found it useful to get this feedback. Sometimes I converted the meme into a proper bug report; sometimes I responded to the meme with an explanation.

Not everyone will use Memegen in the same way. But quite often a high voted meme can be treated like a high voted bug report. It provides signal to the team.

Note that I worked on internal tooling. External facing teams have lots of other feedback channels, and they know that Googler's feedback is biased. So how the team responds to the feedback can be vary a lot.

Is there a way to set the default unit? I'd prefer to see the information per 100g by default (instead using random units).

For security reasons, the VSCode marketplace is not accessible, but many (in the 3-digit range) external extensions have been imported. One technical limitation is that some extensions are not designed for the web (e.g. try to run local things).

As far as I remember, this "IDE in cr/" explanation was found afterwards.

I'm not sure about the dates. At some point (2014?), the use of IntelliJ was discouraged in favor of Eclipse. One year later or so, the decision was reversed and the effort focused on IntelliJ (and Eclipse were considered deprecated).

I can't check when Cider got started. I was probably wrong (it wasn't much used in my circles at that time), I'll update the post.

I like the approach in Lingua Latina per se Illustrata (sometimes called the "natural method"). I've noticed that it was adapted for other languages too, but most of the adaptations seemed old and outdated.

Recently I was wondering if I should work on a modernization of the concept (using audio and a more interactive medium). If anyone has thoughts on this topic, I'd be happy to discuss more.