I tried this model and if I recall correctly it was horribly over-trained on Python test questions to the point that if you asked for C code it would say something like "you asked for C code but specified answer must be in Python , so here is the Python ", even though I never once mentioned Python.
EmailEngine author here. The commenter tried the EmailEngine trial back in 2024 and appears to have had a negative experience. Since then, he’s repeatedly criticized EmailEngine and related components like the ImapFlow IMAP library, often while promoting his own product.
It’s a great honor to be able to talk with Andris. A few months ago I learned that the author of EmailEngine not only created EmailEngine, but is also behind many foundational Node.js email libraries that are widely used. My own projects, RustMailer and Bichon, are built on the shoulders of many great Rust email libraries. EmailEngine is undoubtedly a success, and Andris has spent years quietly and diligently contributing to these core libraries. I have deep respect for you.
It's slow, unreliable, very feature-limited, and extremely expensive for what it is.
Especially these days, you could vibe-code something an order of magnitude better within a day or two and not be locked into a single author's rat's nest of code.
At this point, almost all new EmailEngine customers are AI startups. These are teams that know how to use LLMs well, which makes it interesting that they still opt for EmailEngine despite the extremely expensive $83/month price tag.
Thank you for sharing. I feel similar to you; jealous this system works for others, sounds like a dream, but too overwhelming for me once it hits some point of no return. Your structure sounds interesting.
I'm genuinely curious how others do not get overwhelmed or sucked into yak-shaving some reorganization of a system like this.
I wonder if this would be a simple (limited) example of defeating the watermarking? Surely there's no way SynthID is persisting in what is now a handful of pixels.
reply