I thought for a moment there was a Dark Souls 4
Fucking abbreviations. Who knows it's DeepSeek, Dark Souls or DualShock? All possible on HN.
Could be Death Stranding too
A few words on DS4
161–170 of 197 posts
Re: A few words on DS4
#162When I ran DS4 Q2 the other day (without the new update Q2 imatrix) it was behaving quite poorly after a few agentic turns with opencode, it couldn't modify the files it was telling me the work was ready and didn't use any tool to update files
The bugs were on the API tool call handing. The model worked well. I would retest with updated code and gguf and I and many others never saw it missing anything obvious. Reliable tool call and reasoning. The project is a few days old so certain agents / API combinations definitely had DSML related issues.
I retested and it’s much better now. Wow !
Re: A few words on DS4
#163Earlier quoted context omitted.
That's the flash version not the full model and only at Q2-3~ so while impressive it's still quite different from the full model.
Not really. I'm building now another fast C compiler with DeepSeek 4 Flash, and rarely have to step outside to use Pro or Sonnet, gpt or kimi-2.6. Flash is very capable of almost everything.
which harness are you using? pi? opencode?
Re: A few words on DS4
#164It is a big thing for sure to have a competitive local agentic model. I've replaced gemini 3 flash preview with DeepSeek v4 flash for all of my personal use cases. Starting from chat app, language learning, and even hobby coding. For coding, I couldn't get decent results no matter which sota latest models I used before. It's not close to Opus or Codex models. It's a flash model and makes mistakes here and there (I ju…
> I wish I can run a competitive oss model on 32GB machine in 3 years. It's so hard to predict what size the open-weight models will be, even in 6 months time. Will a 96GB machine turn out to be a complete waste of money? Who knows.
Why would it be?
Today’s models, today’s usefulness doesn’t disappear tomorrow.
Re: A few words on DS4
#165Earlier quoted context omitted.
Not really. I'm building now another fast C compiler with DeepSeek 4 Flash, and rarely have to step outside to use Pro or Sonnet, gpt or kimi-2.6. Flash is very capable of almost everything.
which harness are you using? pi? opencode?
That's not a harness. That's an agent cli. A harness is something completely different. Wish people could use proper terminology.
A test harness is a collection of software and test data configured to test a program unit by running it under varying conditions and monitoring its behavior and outputs. It automates the execution of test suites, providing the necessary stubs, drivers, and runtime environments so developers can isolate and verify specific code components.
I use opencode (lockedcode is still vaporware), claude, kimi and codex.
And most models. Just no Google models so far, I don't trust them.
Re: A few words on DS4
#166Earlier quoted context omitted.
How’s the token throughput / response time?
Healthy! prefill: 30.91 t/s, generation: 29.58 t/s From https://gist.github.com/simonw/31127f9025845c4c9b10c3e0d8612...
Someone is working on a fork that is optimized for M5, might be worth a look: https://github.com/Swival/ds4-m5
Re: A few words on DS4
#167I thought for a moment there was a Dark Souls 4
I thought Future put out a new album.
Re: A few words on DS4
#168I'm very curious where we will saturate the curve on "enough" intelligence for coding. At some point, you can let a less smart model hammer at a problem for longer and get to the same result, and as long as you are not involved it comes to the same thing. I feel like DeepSeek V4 Pro is nearly there. Maybe Flash is too. Once we hit that point, I am curious how much of Anthropic's current business model falls apart? So…
> At some point, you can let a less smart model hammer at a problem for longer and get to the same result, and as long as you are not involved it comes to the same thing. Is that true? I find the smarter models can just be effective when smaller models can't. It isn't a matter of just waiting longer.
I think you're correct with the standard thinking approach (just generate a big stream of tokens before drafting your actual answer). After a while, additional thinking just results in loops.
The RSA approach from https://rsa-llm.github.io/, expanded on by https://www.zyphra.com/post/zaya1-8b, looks like a promising way to squeeze a bit more intelligence from a small model. As I understand it, running multiple independent thinking traces in parallel gives you a chance of one of them finding a different local optimum, whereas running a single trace for longer is likely to just circle around one optimum.
That said, at the end of the day, there's only so much information a small model can contain. If a model just doesn't know some key piece of information, no amount of thinking will help it figure out a solution that depends on that information.
Re: A few words on DS4
#169Earlier quoted context omitted.
Healthy! prefill: 30.91 t/s, generation: 29.58 t/s From https://gist.github.com/simonw/31127f9025845c4c9b10c3e0d8612...
Prefill is 400 t/s in that hardware. Just if the prompt is very short you can't see the real speed and it will default to single token context processing.
Hah, that's my fault for just using "Generate an SVG of a pelican riding a bicycle" as my test prompt!
Re: A few words on DS4
#170Earlier quoted context omitted.
which harness are you using? pi? opencode?
That's not a harness. That's an agent cli. A harness is something completely different. Wish people could use proper terminology. A test harness is a collection of software and test data configured to test a program unit by running it under varying conditions and monitoring its behavior and outputs. It automates the execution of test suites, providing the necessary stubs, drivers, and runtime environments so develope…
Harness: a piece of equipment with straps and belts, used to control or hold in place a person, animal, or object.
So yes the generel meaning applies to test setup and running and also to the agent cli which is the harness for the model.