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

Using an open model feels surprisingly good

matthewsaltz.com

Post reply on HN
Print view View original

61–70 of 157 posts

Re: Using an open model feels surprisingly good

#61

Post by hangonhn »

Gigachad wrote: post #29
wps wrote: post #27

Earlier quoted context omitted.

I’m the exact same way. $15 on openrouter lasted me so long it would’ve got me fired at FAANG. Despite this, my number of commits is dramatically higher. Small, beautifully scoped changes is just good software development, and good for the wallet as well. I think the issue is that no one is content with incremental progress. We all know one shots are mostly possible, so the age of the personal project is kind of over…

I can see why Anthropic is freaking out right now. China has undermined their whole business. AI models will be basic commodities where hosting providers earn a tiny margin over the raw costs rather than the predicted fortunes from being the gatekeepers to the technology.

Yeah I feel like China and their OSS model companies really did the world a great service by ensuring closed source US companies don't have an monopoly on LLMs and thus capture all the value of AI development and its impact on society. It's not going to be the foundational labs that will capture all the value -- I'm sure they will do just fine. A lot of it now will flow to the companies providing the inferences and since no one has any exclusive deals, those companies will have to compete and drive the price down, which ultimately benefits the rest of us.

Re: Using an open model feels surprisingly good

#62

Post by c7b »

loire280 wrote: post #7
irishcoffee wrote: post #2

It surprises me that this concept took as long as it did to gain traction in… hacker news. 15 years ago folks here were compiling kernels and gentoo distros. Lately it’s been “you should just pay the man, it’s cheaper than running these things yourself”

Rolling your own Linux is nearly free and could be done on any computer you had lying around. Dropping >$5k on a computer to run a local model (badly) doesn't really scratch my "hacker" itch. The author of this article works for an AI infrastructure company and ran Kimi K3 on their infrastructure - this post reads like marketing.

The inflation-adjusted cost for getting one of the early personal computers to do some BASIC programming was probably a lot higher than $5k today, and you could still go cheaper. Local AI is still (expensive) hobby territory. A capable local AI machine runs for about as much as a good mountainbike.

Re: Using an open model feels surprisingly good

#63

Post by scorpioxy »

Aquitard wrote: post #50
wps wrote: post #19

The reason Claude code is so popular is because it’s really good at taking super vague human prose “Claude build me a million dollar SaaS”-type prompts and spitting out thousands of lines of code which cover tons of surface-level edge cases, build in tons of functionality, etc The smaller/open models are less good at that. But that’s not how software development is done. You don’t prompt a whole app and be done with…

This is what I've found and would likely be the consenses of the HN community. This has lowered the barrier of entry for many non-SWEs. I'm primarily a data scientist myself in the environmental sector with limited front end development. My partner proposed an idea to help manage her horses and over the course of several weeks we fleshed out an android app that would enable/assist her with horse care. I spent a few d…

Question if you don't mind. Would you have considered outsourcing the application you mentioned? As in, paying someone else to do it?

To me it is great that LLMs are allowing more people to use computers and software the way they were meant to. But the people that are using them this way, in my opinion, wouldn't have commissioned anybody to do it anyway. They'd just live with whatever process/pain they have. So jumping from "I can now produce a prototype in a weekend" to "software development is dead" has always felt strange to me. Just something I've been thinking about lately.

Re: Using an open model feels surprisingly good

#64

Post by shepherdjerred »

danny_codes wrote: post #55
shepherdjerred wrote: post #47

I’ve enjoyed using Kimi K3. The biggest issue for me so far is finding a good harness. Claude Code is excellent for tasks that require backgrounding processes/agents, or fanning out. Codex and OpenCode I’ve found to be less capable.

I suspect FOSS will converge/create a best-in-class harness within the next 6 months or so. As will most (all?) software, the FOSS stuff somehow always ends up being way better than the closed source stuff.

I am not sure -- Anthropic probably does benefit from the vertical integration here. They can train their models to work better with CC, which isn't really an option for third party harnesses.

With that said I think Codex/Kimi code are all behind CC as well, so maybe it's a question of effort and not the model.

Re: Using an open model feels surprisingly good

#65

Post by cpursley »

Gigachad wrote: post #20
wps wrote: post #19

The reason Claude code is so popular is because it’s really good at taking super vague human prose “Claude build me a million dollar SaaS”-type prompts and spitting out thousands of lines of code which cover tons of surface-level edge cases, build in tons of functionality, etc The smaller/open models are less good at that. But that’s not how software development is done. You don’t prompt a whole app and be done with…

Personally I've found Deepseek v4 Flash to be as useful to me as Opus. But I don't do these silly one shot tech demos. I have the technical understanding to ask for exactly the change I want with the right terminology. I loaded up some credit on openrouter and it took me ages to hit $1 in spend.

Which harness? I tried Kimi on Opencode Go and after an hour I hit my 5 hr limit and went back to Codex.

Re: Using an open model feels surprisingly good

#66

Post by shepherdjerred »

seaal wrote: post #56
danny_codes wrote: post #55

Earlier quoted context omitted.

I suspect FOSS will converge/create a best-in-class harness within the next 6 months or so. As will most (all?) software, the FOSS stuff somehow always ends up being way better than the closed source stuff.

Is there any resource or benchmark actually comparing how different harnesses perform with a given model? Really just feels like endless FOMO with how fast the iteration cycle is for harness and model development.

I found this: https://artificialanalysis.ai/agents/coding-agents#harness-c...

I don't think it's very good though. As an example I can use one CC instance to delegate to several to achieve complicated/open-ended goals.

That just isn't possible with other harnesses, and it's definitely not benchmarked.

Re: Using an open model feels surprisingly good

#70

Post by arjie »

ilteris wrote: post #60
arjie wrote: post #31

Earlier quoted context omitted.

Haha! Love to hear it. That's exactly what I have too: a claw-like[0] system which I originally used Sonnet for and now use my DeepSeek v4 Flash with. In my case, I was foolish enough to run it all on my hardware which is pretty damned fast but has a duty cycle of 5% and runs idle most of the time. It's definitely better done via API. Tell me more about the Alexa-like system! I have mine at home on a custom OpenWakeW…

Nice setup. Which home assistant do you use? I would love to bring alexa like capability to my setup.

Like the others I just wrote a simple agentic loop that listens to telegram and acts with a timeout to check other things, and with a timer to run scheduled jobs on a cron.

EDIT: Oh, home assistant. I use Home Assistant https://www.home-assistant.io/

Post reply on HN