TechPulseTechPulse
Back to News
Advertisement
Advertisement

⚡ Community Insights

Discussion Sentiment

50% Positive

Analyzed from 95 words in the discussion.

Trending Topics

#deepseek#context#model#flash#quality#openai#https#models#talking#degradation

Discussion (4 Comments)Read Original on HackerNews

sibidharan•about 3 hours ago
Which models are we talking about? Is there any degradation in quality, long context retrieval?
ninju•18 minutes ago
It depends on how mature the DeepSeek model became before OpenAI noticed that they were wholesale replicating their model and starting blocking access

https://www.reuters.com/world/china/openai-accuses-deepseek-...

throwa356262•about 1 hour ago
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

wilbur_whateley•about 1 hour ago
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.