Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek V4 Flash 0731

arcprize.org

Post reply on HN
Print view View original

471–478 of 478 posts

Re: DeepSeek V4 Flash 0731

#471

Post by re-thc »

edot wrote: post #458
re-thc wrote: post #136

Earlier quoted context omitted.

> In the $150/mo range you can get effectively unlimited usage of GPT 5.6 Sol (Pro plan) Not true. Sol on XHigh or Max runs out even on the $200/mo plan. It's not close to effectively unlimited. Maybe at 2x the current allowance it can.

What are you doing where you're getting Sol on XHigh or Max to run out on the $200 plan? Last night, I had 48% of my weekly limit left, so I spun up 4 projects I had been working on and ran them all on Ultra with Fast mode and /goal, and it took over 4 hours to burn through that. I mean, I was reeeeally trying to use it up because I just can't use it up with normal usage for weekend and after-work programming. I've h…

> What are you doing where you're getting Sol on XHigh or Max to run out on the $200 plan?

Real work. $200 looks good on the outside until the essence of it, e.g. the models lie. I gave a list of spec to Sol and Sol decided some items didn't need to be done and the reason was "unproven", "not enough evidence", etc.

They all come up with amazing ways to lie (or be lazy). Often times what you get isn't what you asked for (only on the surface). E.g. I ran it to iteratively bench and optimize a better data structure for the project. It spent hours and finally came up with something. When I check it out -- it benchmarked the wrong criteria and was way off. So here we go again. Most AI work looks good on the surface. There are infinite edge cases.

So to do real work and gate it you need to:

1. Plan

2. Get it to do the work

3. Get independent agents to check from different angles

4. Take that feedback and get it to fix those gaps

5. Match against the plan and redo parts if needed

Every task is easily 4-5x the estimated amount of tokens.

p.s. well I did burn some banked resets building a compiler for some language AND it is still NOT done. Every time it says done I say check it says ok we still have bugs...

Re: DeepSeek V4 Flash 0731

#472

Post by yogthos »

FernandoTN wrote: post #194
abixb wrote: post #162

Earlier 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…

What you're overlooking is that any large task can, and should, be broken down into smaller individual components that can be reasoned about and tested in isolation. This is literally the whole basis for how we do programming. You don't need a model that can keep track on a gargantuan tasks all at once. You need a process for breaking problems down into manageable chunks, and then assembling them into a solution. This is a problem that can be solved by a harness through steering and and having a decent agentic loop.

Re: DeepSeek V4 Flash 0731

#473

Post by ExxKA »

abixb wrote: post #162
LaurensBER wrote: post #9

I'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…

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…

It is true.

I have been using it since it got released and its as good for scoped coding tasks, as the other big models I use, but just soo much cheaper.

Re: DeepSeek V4 Flash 0731

#474

Post by taf2 »

Got this up and running at 250 tok/s about 2500 agg tok/s for 16 users and now this morning got https://huggingface.co/webbrain-one/DeepSeek-V4-Flash-0731-V... working - patched it to support multiple images... should post this soon to huggingface - having about gpt-5.6 terra high locally feels pretty good

Re: DeepSeek V4 Flash 0731

#475

Post by retinaros »

vijucat wrote: post #456

Caching makes a huge difference to cost. On Fireworks AI, for example, if it hits the cache, you pay only 20%. And uncached is just $0.14/M tokens for DSV4-0731! I get entire re-architecture projects (with new tests and documentation) done for mere dollars. DSV4-0731 is a daily driver for me. But note that you have to use Cline (or other harness) if using vscode. I was shocked at how poor the recent versions of GitHu…

many are buying into routing as a way to save money but it destroys the cache savings. prob that is what copuilot is doing

Re: DeepSeek V4 Flash 0731

#476

Post by nwienert »

debazel wrote: post #406
jfaat wrote: post #375

Earlier quoted context omitted.

That's fascinating, it's WAY better than luna ime. What sort of things are you testing it for?

I've been using this DeepSeek model the whole day today after building with 5.6 Luna extensively over the last week and I would disagree, at least for Rust + OpenGL. DeepSeek just spend almost 2 hours trying to figure out why terrain textures were not working. It tried everything over and over again, it even had reference code for meshes on how to setup the rendering with materials, and it could just not do it. I fin…

That's roughly my experience. Luna is extremely efficient and at higher levels of reasoning and longer running tasks more capable.

Reading the DS reasoning is wild, it's constantly going in circles. The most minor lack of clarity in your prompt and it will spend ages going back and forth on what you meant. It reasons 5x longer than the preview which makes it really slow now as well. We did a lot of work to nudge it to be decisive and improve our evaluation setup to there's more clarity, and it helped but only marginally.

Ours is a full-stack app one shot test so it includes backend, frontend, design, and QA/testing. It's graded by Opus xhigh and Sol xhigh and the grades are averaged.

DS4 preview would finish in 20 minutes flat on high reasoning and grades 6/10. Luna high gets 9/10 in about 30 minutes. DS4-final is crazy - at high thinking it's taking over an hour and getting ~8 but only had one successful run as I got tired of waiting so long after many early abort/retries trying to debug why thinking was so long. The lowest thinking still takes over 45 minutes, and with thinking off it actually is finally closer to preview in time but actually get's a much more varying result anywhere from incomplete to 6 it seems.

Costs per run DS4 is best but not actually by a lot as it's spending 10x the tokens with all the reasoning and mistakes. It's a very brute force model and I really preferred preview in many ways for how predictably fast it was.

Side note, Spark 1.2 is a nice model for this test, best in frontend design and fastest to get results together, though not nearly as efficient as Luna. Grok scores similarly to Spark but at like $50/run vs the contributor Spark costing $1.50.

Edit: was curious to see and seems DeepSWE agrees at least: https://www.together.ai/blog/deepseek-v4-flash-0731-vs-gpt-5...

Edit 2: btw it tests a team of agents working together in a special harness and stack. So 20 minutes is for 8 agents essentially. That said everything was built around DS as it was the cheapest to iterate against so even with that advantage the new one struggles.

Re: DeepSeek V4 Flash 0731

#477

Post by kgwgk »

paxys wrote: post #151
rain_iwakura wrote: post #123

Earlier quoted context omitted.

not at all true. if you're truly using it across the board for smaller things (translation of pages, filtering of every individual tweet based on its relevance to you etc), the costs ramp up super quickly. i used for work where i did less and it quickly reaches thousands if you're not careful. i can already see what some will say: skill issue et cetera - whatever.

$100-200/mo is the subscription price. You aren’t going to go over. And you can select smaller models as well. Not everything has to be done by the most expensive one.

>> you can get effectively unlimited usage of GPT 5.6 Sol (Pro plan). Why use a much weaker model for the same price?

> Not everything has to be done by the most expensive one.

Ok then.

Re: DeepSeek V4 Flash 0731

#478

Post by treetalker »

EarthAmbassador wrote: post #460
ray_kay777 wrote: post #314

Earlier quoted context omitted.

I think we're even starting to reach that saturation point now for a lot of people. In my industry (law) plenty of people have tried CoPilot once or twice, or tried ChatGPT a year ago, and as a result have basically dismissed AI as being useless. The setup required to be able to get it to do end to end tasks to your liking is also substantially more work than most people are willing to put in.

I find 500x returns on my $20 Chat GPT and Claude subscriptions as I litigate pro se against large law firms in federal court.

Case numbers? I'd love to take a look at the dockets.
Post reply on HN