Hacker News Reader

Comment by christophilus | Hacker News Reader

I've been working with Deepseek V4 Flash (with opencode as the harness). It's been almost indistinguishable from Codex / Claude Code for me. I'm sure I'll run into problems when I get to a stickier ticket to tackle. But so far, it's been quite good, and I find it writes straightforward code.

I do think the Chinese models are good enough for an 80/20 rule use case.

View on HN

I also use DeepSeek v4 flash and v4 pro, but I can’t settle between using Claude Code or OpenCode and it seems like I waste time switching back and forth (especially keeping my personal SKILLs files synced). On one hand, a ton of engineering work has gone into Claude Code, on the other hand all Chinese models I have tried with OpenCode seem well configured out of the box.

I was thrilled to have Gemini Ultra for a month and use as many Opus tokens with AntiGravity as I could use, but I am happier using less capable models like DeepSeek knowing that it is more fun to do more of the work myself, it is a smaller hit on the environment, and incredibly cheaper.

We have switched approx 80% of our work to deepseek, and it works great. Our setup is a bit unconventional though, we upload all cot / sessions to shared storage and generate centralised project level context. We've found this is helpful in directing and working with these slightly less sota models and getting great value for ai spend.

I'm planning to open source all this infra soon, hopefully useful for others too.

I tried Deepseek V4 Flash with very low expectations and was pleasantly surprised. It's a surprisingly capable model for the price.

What provider(s) do you use?

Not op but I use their official platform. Cheapest token top-up is $2.12

I use Pro because I’m insensitive to the price difference, but also found Flash very capable in OpenCode.

That v4 quality is available to everyone in the world for a pittance is beyond remarkable.

it would be a really great option if it didn't lack vision

what do you use vision for? I have failed to find a workflow with it that makes sense, asking it to review screenshots of websites or whatever it misses extremely obvious details like text flowing out of it's container/overlapping other text, things being in entirely the wrong place, etc.

What models have you tried? Gemini 3.1 pro has vision capable of reading my sloppy diaries from 10 years ago, down to small glyphs and doodles.

I mean they mostly work for OCR, I meant in a coding context.

reading pdfs

this is mcp or custom call to lowest cost model

someone did a webcam + agentic + capture of other computer bios/boot -> upload to image model -> back to agent

For coding?

reading pdfs

Reply on news.ycombinator.com