Hacker News Reader

Comment by alecsm | Hacker News Reader

I've been using the last Deepseek Flash update for a week and I'm amazed. It was a capable model for easy tasks but now it looks like it can do some heavy development for peanuts.

I can't wait to try this new one.

View on HN

IME I can't trust it to write it's own plans from a spec, but if I give it a detailed execution plan written by Opus, it's fast and cheap (if chatty) in executing it.

This is what I do, and it works fantastically well. Just make sure you have Opus/GPT review after.

Interesting. I use Flash for making the plans and GPT for execution.

Depending on the language you're writing in and the problem domain, the smaller models can do dramatically better or worse.

I suspect in the future we'll see language-specific small models. "Coding" is still pretty broad as an activity. It'd be nice to be able to load up a model specific to, say, class-based Python and run it on-device.

Harmonic's Aristotle is a sort-of language specific model for Lean, if you want to see the future you described today.

flash for plans?! i don't understand why you wouldnt use something far stronger for the most load bearing point of the project

Price obviously

There aren’t many “far stronger” models than Flash 0731 now, it’s only beaten by Claude and OpenAI models at high/max effort, and everything that matches it costs 5x-10x more.

You're doing it backwards.

I find DeepSeek flash incredible for the price and good in general if it has good plans. I will typically plan using Opus or GLM, then implement with DSF

Reply on news.ycombinator.com