Remix.run Logo
▲ skeledrew 3 hours ago

All that keeps jumping out at me is how they've set it to refuse giving users thinking tokens and prompts for full reasoning in output. Just drives me further away; I may not stop using Claude completely for now, but I'll be moving even more of my primary workload to Chinese providers. That's where openness and freedom is now at.

▲rajeevk 3 hours ago | parent | next [-]

What Chinese models/providers are you using for this? I'm hitting Claude's weekly limits much sooner than I used to with roughly the same workload, so I'm interested in trying alternatives, especially ones with strong coding/agentic performance.

▲arcanemachiner 2 hours ago | parent | next [-]

Get yourself an OpenCode Go subscription and give DeepSeek Flash 4.1 a shot.

A common tactic is to used a big brain model like Opus for planning and reviewing, and a cheaper model for execution.

▲Amekedl 23 minutes ago | parent | next [-]

While it's a common tactic, and I'd vouch for it if you don't really know what you want to code in fact, but if you know what you want to get out of it, I haven't found anything I'd need opus 5.5 for instead of deepseek-flash (flash v4.1 hosted via platform.deepseek.com)

▲gobip 9 minutes ago | parent [-]

genuine question: is there an improvement in using platform deepseek com, over openrouter and a third party provider?

▲lukan 2 hours ago | parent | prev | next [-]

In my experience that tactic works well if the codebase is limited in size, or well maintained and separated. Otherwise I do notice a difference also letting fable do the execution, not just the planning for complex tasks.

▲criley2 an hour ago | parent [-]

In my experience it never works well on any real work. In fact, I'd go the opposite, plan with the dumb model and execute with the smart model because at least the model writing the code and solving the emergent problems is capable.

In my experience (and I've been trying this a bunch): smart planner + dumb executor produces worse code with higher spend than simply using the smart planner to do both.

It's easy to understand why:

- If the planner has truly thought the issue through, properly designed the solution, solved all of the emergent problems, then the final "write" of the code is just a few more output tokens.

- If the planner has NOT truly planned the issue completely, then you're letting a substantially dumber and less capable model make significant decisions, and trusting its problem solving, without having a better model check it.

If you're highly cost conscious (paying for your own tokens and not making any money) then you have no choice but to trade your time and effort for tricks like this to save money by lowering the quality of your output.

But if your employer is paying for tokens: just use the smarter model. You save your time preventing re-work and reducing code review, you save your employer money (primarily from the cost of your own labor and reduced rework), and you get a better output every time (Opus 5.5 mogs Deepseek 4.1 flash in every single way except cost).

▲fosron 2 hours ago | parent | prev [-]

Been using DeepSeek Flash 4.0 and 4.1 for some random sideprojects via OC GO, its a great deal and for non-corporate work it's really great!

▲surgical_fire 2 hours ago | parent | prev [-]

I have tried GLM on a subscription, and also DeepSeek and MiMo using API directly. MiMo in particular is extremely cheap.

For regular software development they have been pretty great.

▲pllbnk 3 hours ago | parent | prev | next [-]

Crazy how tables have turned. Life seems surreal since 2020.

▲wg0 an hour ago | parent | prev | next [-]

If you're not a noob and you know what you're doing then I can't recommend DeepSeek v4.1 Flash (set to high) enough.

▲kabes an hour ago | parent [-]

What's special it that noobs shouldn't use it?

▲kouteiheika 24 minutes ago | parent | next [-]

In general the weaker the model the more skill you need to drive it (at least if you care about quality).

▲wg0 34 minutes ago | parent | prev | next [-]

Noobs are burning tokens like "make me an app that does this" whereas an experienced engineer would go with certain language, framework and architecture in mind.

▲dubcanada 38 minutes ago | parent | prev [-]

It is not as self thinking, you need to be more detailed and accurate with the prompts.

▲intended 38 minutes ago | parent | prev | next [-]

I think we need more of these issues to frustrate people.

There is a fundamental incompatibility between “safe AI” and compliant AI.

This is an issue when it’s people, Enron or Madoff for example.

I guess it’s : “safe AI, capable AI, and obedient A. Pick one “

▲hannesv 3 hours ago | parent | prev | next [-]

What Chinese provider would you use that is on par with Claude code?

▲arcanemachiner 2 hours ago | parent | next [-]

Since Claude Code is a harness that can be made to work with (pretty much?) any model, the answer to the question you have asked is: Claude Code

Non-pedantic answer: I totally agree with you. Opus 5.5 is totally knocking it out of the park IMO.

▲xandrius 2 hours ago | parent | prev [-]

Zoo Code is so much better than CC that to me even using similar models I go for CC for simpler things and ZC for larger work.

▲shaan7 3 hours ago | parent | prev | next [-]

Yeah its annoying. I need to pay for thinking, but I can't see it :/

▲OtomotO 3 hours ago | parent | prev | next [-]

Ironic, especially given 100 hundred years of Hollywood proaganda telling the west that the US are the center of freedom.

Which was and is true to some extent.

And don't get me wrong, China is a dictatorship, and a tyranny for some.

But then again, the west is a tyranny for some.

▲muzani 3 hours ago | parent [-]

That's how the cycles happen. China realizes they could use a little more freedom and US realizes that they could do with a little less. The emerging/shrinking middle class of both countries also moves the sweet spot.

▲OtomotO 2 hours ago | parent [-]

Absolutely!

Doesn't make it any less amusing from the outside, to see the US struggle with their identity. (It's most always just a struggle when freedom becomes less)

▲gadders 2 hours ago | parent | prev [-]

I mean there is a good reason for that, no? Distillation is an issue.

▲AndroTux an hour ago | parent [-]

Not an issue for me, the end user.