I'm curious about the differences between DeepSeek R1 0528 and the original R1 model. Are there any significant improvements or issues that you've noticed with the new version? I'd love to hear about your experiences with it!
9 Answers
I had issues with the old R1 version giving me constant API errors, but R1 0528 never threw those errors at me. I just used it to create a WordPress plugin, and it worked perfectly! Just miss being able to send images as context like with Gemini.
The way it processes information has improved too; it seems like they really focused on enhancing the logical flow and reasoning this time around.
In my testing, it showed much better performance with coding tasks. It’s more complete and less error-prone now and actually addresses mistakes when you point them out—unlike the first R1, which struggled a lot.
It definitely seems to engage in longer conversations now—less abrupt!
I’ve tested math functions, and only DeepSeek R1 0528 got tricky problems like 9.9-9.11 right. It’s impressively accurate!
It feels like R1 0528 has the smarts of the old R1 but the composure of V3. The first R1 behaved unpredictably, but this new version is much more controllable and reliable!
From what I’ve seen, it returns shorter responses—about 60% less lengthy—and uses 50% more elaboration. Plus, I’ve noticed it goes crazy with emoticons—three times more than before!
Hmm, interesting point!
One major upgrade is that it can now think in multiple languages, not just English. It even passed my native language poetry test, which is a big step forward!
It was able to handle Russian in the previous versions; good to see it's retaining that!.
Yo mama!
ChatGPT free gets it right all the time, though!