I wanted to start a broader community experiences thread around DeepSeek.
A useful angle is evaluation, but it also connects with prompt design. Different tools and workflows can produce very different results even when the goal is similar.
It would be interesting to compare practical examples, experiments, setups, or lessons that show where DeepSeek is genuinely useful and where it still needs improvement.
A useful angle is evaluation, but it also connects with prompt design. Different tools and workflows can produce very different results even when the goal is similar.
It would be interesting to compare practical examples, experiments, setups, or lessons that show where DeepSeek is genuinely useful and where it still needs improvement.