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.
throwa356262 5 hours ago [-]
I agree that Claude is better (definitely better than the flash version which is relatively small). But...
I actually canceled my Claude Code plan a few months back after trying out some of the "lesser" models on openrouter. They seem to work as just as well (or just as bad) for my coding tasks.
jst1fthsdys 3 hours ago [-]
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?
wilbur_whateley 52 minutes ago [-]
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.
rjh29 2 hours ago [-]
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
agentbc9000 5 hours ago [-]
[flagged]
ninju 5 hours ago [-]
It depends on how mature the DeepSeek model became before OpenAI noticed that they were wholesale replicating their model and starting blocking access
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.
agentbc9000 3 hours ago [-]
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.
dpoloncsak 3 hours ago [-]
Hardware made in China, while can still have issues, is not nearly the problem that software running on servers in China is
bagol 3 hours ago [-]
What's wrong with China?
akomtu 2 hours ago [-]
China is fine. The Communist regime is the problem.
jst1fthsdys 2 hours ago [-]
How is it a problem? Say, compared to the... democratic regime here in the US?
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
I actually canceled my Claude Code plan a few months back after trying out some of the "lesser" models on openrouter. They seem to work as just as well (or just as bad) for my coding tasks.
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?
https://www.reuters.com/world/china/openai-accuses-deepseek-...
But China?