> to DeepSeek
But China?
I cut my AI API costs 99% by switching from Claude to DeepSeek
11–20 of 23 posts
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#12> to DeepSeek But China?
We use DeepSeek's API for summarisation only — no sensitive data, no user data, no fine-tuning. It's article text that's already public. The Supabase database is where the AgentDB data actually lives and that's fully in our control.
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#13> to DeepSeek But China?
Fair question. How much of the tech in your stack is made in China? Your iPhone, your laptop's rare earth minerals, the Amazon servers half your SaaS runs on... nearly everything.
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#14Earlier quoted context omitted.
The tweet mentioned deepseek V4 flash. From HF: 284B parameters (13B active), 1M context window. This is indeed some kind of compressed context and the quality goes down as the context grows. IIRC the V4 paper had some numbers on this https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
V4 flash is much worse than any Claude model. If you're doing something simple, it can be a good way to save money though.
Define "much worse". I use DS v4, GLM, and some Kimi with omp personally, and have Cursor with latest Claude and GPT models at work. I notice zero difference in the work for my workflow between Opus and DS.
Really confused how people make these claims. Are you just basing this off benchmarks or your own personal work? Are you an experienced dev or just doing vibe coding?
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#15> to DeepSeek But China?
Fair question. How much of the tech in your stack is made in China? Your iPhone, your laptop's rare earth minerals, the Amazon servers half your SaaS runs on... nearly everything.
Hardware made in China, while can still have issues, is not nearly the problem that software running on servers in China is
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#16> to DeepSeek But China?
What's wrong with China?
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#17Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#18Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#19Earlier quoted context omitted.
V4 flash is much worse than any Claude model. If you're doing something simple, it can be a good way to save money though.
Define "much worse". I use DS v4, GLM, and some Kimi with omp personally, and have Cursor with latest Claude and GPT models at work. I notice zero difference in the work for my workflow between Opus and DS. Really confused how people make these claims. Are you just basing this off benchmarks or your own personal work? Are you an experienced dev or just doing vibe coding?
Huge variation in how people prompt and use their models. Vibe coding with ambiguous requirements vs. multiple steps of precise planning are completely different imo
Re: I cut my AI API costs 99% by switching from Claude to DeepSeek
#20Earlier quoted context omitted.
V4 flash is much worse than any Claude model. If you're doing something simple, it can be a good way to save money though.
Define "much worse". I use DS v4, GLM, and some Kimi with omp personally, and have Cursor with latest Claude and GPT models at work. I notice zero difference in the work for my workflow between Opus and DS. Really confused how people make these claims. Are you just basing this off benchmarks or your own personal work? Are you an experienced dev or just doing vibe coding?
My own experience. I'm working on something complex that's not in the datasets these models were trained on. There I see V4 flash breaking down and hallucinating much more often than GPT/Claude. For normal, common tasks, I also don't see much of a difference.