Comment by postalcoder

1 day ago

I hope DeepSeek takes some time to improve their tuning for reasoning effort. Right now, there are only three reasoning efforts: low, high, and max.

For all intents and purposes, "low" is pretty much the same as turning reasoning off, and "high" is similar to "max". "High/max" performs way too much reasoning, takes forever, and causes costs to balloon. They need a proper "medium" setting.

I get it that they're probably focused on pushing performance right now, but the ergonomics of the model aren't great.

3 comments

postalcoder

Reply
iamniels  1 day ago

I switched to GLM-5.3 flash on high for this reason. Too many "but wait" in the Deepseek-v4 reasoning.

  • alfiedotwtf  20 hours ago

    GLM 5.3 Flash was the killer for me. It really feels like we have Claude-approaching models at home.

    I just wish they kept parameter count down in order to fit entirely within commonly used RAM sizes