Earlier quoted context omitted.
I've enjoyed using https://omp.sh/
Seconded. I love OpenCode and Pi, but omp is my daily driver.
What's good about it? I use OpenCode and it does what I need, basically.
DeepSeek V4 Flash 0731
241–250 of 477 posts
Re: DeepSeek V4 Flash 0731
#242Earlier quoted context omitted.
If what you're saying is true and accurate, then US-based AI labs are in big trouble. The only saving grace might be some sort of a 'national security' proclamation banning the use of state-of-the-art Chinese (and non-US) models across US federal and state governments and large enterprises (especially ones with federal government contracts), but even still, US AI labs will probably lose out massively on international…
I think you're overlooking the fact that for long-horizon tasks, even small errors compound over time and can lead to catastrophic outcomes. For simple queries, we have reached the threshold since the beginning of the year, and models are good enough from every provider to make a meaningful difference between one another. (ChatGPT, Claude, Gemini, Grok, MuseSpark, Kimi, DeepSeek, GLM...) The real unlock will be, and…
There are a lot of tasks that are hard for organisations to run consistently but require some intelligence - monitoring logs and metrics for anomalies and security events, backup audits, audit processes in general, ensuring document quality and consistency, database advice and tuning, customer experience management, process optimisation - that are not "long horizon" in the classical sense of each step depending on the last, but are the result of consistency and attention over a long period of time and a large amount of data.
For this genre of task execution can run with limited horizon and is independent but would be too expensive to do with "us frontier tokens", I think for these, there is value in availability of cheaper tokens.
Re: DeepSeek V4 Flash 0731
#243One of the best things about this version is that it is trained in the codex harness. It feels just as good as OpenAI models in using codex tools, but extremely cheap and with 1M context
Re: DeepSeek V4 Flash 0731
#244Earlier quoted context omitted.
I've posted a few times about my project that's a collection of 30k-250k webapps that are served from a WebDAV server. The apps know how to write updated copies of themselves back to the server. My family uses it. I have gallery apps (yearbooks for each year are a lot of fun!) of us on trips and just living, an outlining app that's a mesh of Workflowy and Org Mode (it's called Fluxtral), a markdown-backed app (it use…
A collection of 30k-250k apps? Like individual unique apps?
Sorry, a collection of apps whose size is between 30kb and 250kb.
Re: DeepSeek V4 Flash 0731
#245Earlier quoted context omitted.
Could you go into how you run two instances that speak to each other in an implementer / advisor role in parallel? I’ve been looking for this sort of orchestrator / worker solution where there’s constant feedback and nudging between the two.
Sure! It's https://omp.sh/ with the advisor mode enabled. You can probably implement something similar as a plugin for your preferred harness. From a technical perspective I think it just sends the output w/h the thinking and tool trace to another model and asks it to double check everything (exact prompt must be somewhere in the OMP repo).
Thanks I’ll give that a go.
Would you run a less costly model as the supervisor given it’s consuming a lot of text and may have a simpler task to do like “make sure the implementing model doesn’t start over-engineering things”?
Re: DeepSeek V4 Flash 0731
#246One thing that popped into my head is that this shows how committed they are to building something that scales across the world
China has zero energy concerns in terms of energy production - not literally zero, but they’d be able to prioritize other dimensions and not necessarily worry about efficiency
Here they are though releasing models that sip resources
Re: DeepSeek V4 Flash 0731
#247I've been using it extensively since the release and the best summary I can give is that it's good enough to use it for (almost) everything and cheap enough that the cost are irrelevant. I'm running it in Oh My Pi with a second instance running as "advisor" and even with 5-6 active sessions (effectively 12 streams) I'm struggling to spend more than 5 bucks per day. OpenCode Go even has double limits temporarily so fo…
Are you using it via the official DeepSeek API, or via a different model provider? If the former, it's worth noting that their cache read prices are one tenth that of every other provider ($0.0028/M vs $0.028/M), so folks who want to use a sovereign inference provider with a zero data retention policy likely won't see anywhere close to the same value.
Re: DeepSeek V4 Flash 0731
#248Earlier quoted context omitted.
As someone who recently tried it on some blackwell cards, it's possible to match the prices especially the input can be even cheaper and output can match the costs so you can easily build a net 20-30% margin business even at current GPU prices. The entire issue is caching, I tried to write some custom to dump to disk kv-caching using some ideas from their papers and my experience with snapshots and vm checkpoint syst…
Mild info dump, since this has a few too many upvotes and some folks might be misunderstanding, 20-30% is assuming a typical agentic workload where input tokens dominate by over 20:1 or at least 10:1, if you are output token heavy then this is going to be a different ball game. And there is no way in hell anyone can afford caching prices same as what DeepSeek is offering, and DeepSeek keeps the cache available for an…
Thanks this is a comment with a great amount of useful detail.
Re: DeepSeek V4 Flash 0731
#249How can OpenAI or Anthropic fight against these prices?! $0.14 input, $0.28 output. For 1M tokens...
Re: DeepSeek V4 Flash 0731
#250Earlier quoted context omitted.
If what you're saying is true and accurate, then US-based AI labs are in big trouble. The only saving grace might be some sort of a 'national security' proclamation banning the use of state-of-the-art Chinese (and non-US) models across US federal and state governments and large enterprises (especially ones with federal government contracts), but even still, US AI labs will probably lose out massively on international…
I think you're overlooking the fact that for long-horizon tasks, even small errors compound over time and can lead to catastrophic outcomes. For simple queries, we have reached the threshold since the beginning of the year, and models are good enough from every provider to make a meaningful difference between one another. (ChatGPT, Claude, Gemini, Grok, MuseSpark, Kimi, DeepSeek, GLM...) The real unlock will be, and…
That doesn’t make sense. It’s not like SOTA models are error free, yet we still use them.
You use Fable 5 right? If that’s good enough for you now, why wouldn’t a Chinese model that’s as good as Fable 5 but at 10% the cost be good enough in 6 months?