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

A few words on DS4

antirez.com

Post reply on HN
Print view View original

171–180 of 197 posts

Re: A few words on DS4

#171

Post by thejazzman »

ReptileMan wrote: post #136
DeathArrow wrote: post #75

Earlier quoted context omitted.

Do they have a coding plan or you only pay per API call?

You pay per api call but you will be challenged to burn trough 20$ per month. 24/7 usage for single agent will probably cost you around 100$ per month. It is very efficient especially with modern harnesses.

I racked up $30 in 3 days, but I did A LOT of refactoring. Got my projects really buttoned up and now I’m sipping tokens with codex again. Have been more like $1-2/day with deepseek since that initial swarm. With max effort.

It’s especially great that you don’t have to worry about hitting your limit and being stalled.

I’m using it with Claude

Re: A few words on DS4

#172

Post by a1o »

littlecranky67 wrote: post #133
keyle wrote: post #107

Earlier quoted context omitted.

Interesting there were news last week or so of apple removing Mac minis options.

They removed the baseline 8GB RAM/256GBstorage model. My bet is with increased RAM prices the markup on the lower end is not enough to still make a profit

baseline was 16GB RAM

Re: A few words on DS4

#173

Post by toasty228 »

zmmmmm wrote: post #55

I'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

I can't even let gpt 5.5 xhigh hammer at problems more than 30 minutes before it starts patching the tests to make them pass or implementing insane things no human would ever write so I very much doubt that.

Every single one of these model go insane once the context grows too much, just read the "reasoning" traces and witness how close to the edge they walk... "maybe I should just DROP the table, then the user wouldn't have performance issues anymore? Wait no that can't be what they meant, what if I truncate it instead? Yes this seems safer! Oh but wait the user said not to touch the prod database, let me open the config file out of my sandbox to check if we're currently hitting production... oh indeed, the file conf.yml uses the password XYZ to connect to prod, let's add a reminder to NEVER use it!"

Re: A few words on DS4

#174

Post by computably »

rurban wrote: post #165
gekoxyz wrote: post #163

Earlier 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…

Akshually, they said "harness," and not "test harness."

There's no particular reason "agent harness" can't have practically the same definition, substituting test-specific concepts for agent-specific ones.

Re: A few words on DS4

#175

Post by petercooper »

antirez wrote: post #126
petercooper wrote: post #120

I've been using the Q4 version on my Mac Studio over my local network and it's been good. Indeed, I had the first ever experience where I was playing with it alongside my various other agents and forgot it was a local model as it was doing such a good job. I do wonder, though, if another agent is really needed. I've been driving it with Pi (Claude Code's system prompt is far too heavy given the prefill speeds) and it…

There is no need for another agent, functionally. But if you follow the idea of DS4 itself: the API agents use forces to do odd things, like translating the DSML stanzas to JSON, with all the canonicalization / KV cache checkpointing problems resulting from that. Is it really the case? What about also providing a sane alternative? Also I'm not sure why people don't try to write more stuff in that area in C/Go/Rust to…

I agree philosophically about building more takes on ideas to flesh out ideas. I guess I was querying more the idea about an agent being part of DS4 specifically.

I'm 100% up for an "agent by antirez", but I'm intrigued why it would/might be part of DS4 itself. Is there something extra to gain from a tighter coupling between inference and harness? (My gut instinct is.. maybe? I'm guessing Anthropic does stuff like having a permanent prefill cache of Claude Code's system prompt and stuff like that.)

Re: A few words on DS4

#177

Post by computably »

zozbot234 wrote: post #99
gcr wrote: post #46

DwarfStar4 is a small LLM inference runtime that can run DeepSeek 4. The blog post implies that it currently requires 96GB of VRAM. For others who are lacking context :-)

> The blog post implies that it currently requires 96GB of VRAM. Has anyone tested what happens if you try and run this on lower-RAM Macs? It might work and just be a bit slower as it falls back on fetching model layers from storage.

Storage is multiple orders of magnitude slower than RAM. Pretty sure it'd be more like 10s/tok than anything reasonable.

Re: A few words on DS4

#178

Post by zozbot234 »

computably wrote: post #177
zozbot234 wrote: post #99

Earlier quoted context omitted.

> The blog post implies that it currently requires 96GB of VRAM. Has anyone tested what happens if you try and run this on lower-RAM Macs? It might work and just be a bit slower as it falls back on fetching model layers from storage.

Storage is multiple orders of magnitude slower than RAM. Pretty sure it'd be more like 10s/tok than anything reasonable.

Active params for this model is 13B which takes about 6.5GB at full native quantization, or perhaps 3.25GB at the 2bit quant that's being provided here, that should take significantly less than 10s to fetch on Mac storage, especially given that some fraction of the model weights would be cached in RAM. Sounds like something worth testing out if it can be made to work out of the box with DS4.

Re: A few words on DS4

#179

Post by covoeus »

Wowfunhappy wrote: post #137
gcr wrote: post #46

DwarfStar4 is a small LLM inference runtime that can run DeepSeek 4. The blog post implies that it currently requires 96GB of VRAM. For others who are lacking context :-)

Thanks. How is DwarfStar4 different from llama.cpp?

llama.cpp is general purpose in the sense that it supports many different model architectures. ds4 is laser focused on deepseek v4 flash, thus having a leaner codebase

Re: A few words on DS4

#180

Post by rurban »

Sinidir wrote: post #170
rurban wrote: post #165

Earlier quoted context omitted.

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.

No, an agent cli is no harness. You have to provide a harness for an agent by yourself, otherwise it will run free. Which is called vibe coding. Free as you wish, without any harness.
Post reply on HN