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

Stable Code 3B: Coding on the Edge

stability.ai

Post reply on HN
Print view View original

41–50 of 148 posts

Re: Stable Code 3B: Coding on the Edge

#41

Post by bearjaws »

londons_explore wrote: post #19
lfkdev wrote: post #6

How is this compared to the current GitHub Copilot?

If you just want to get stuff done, use the best tools like a Milwaukee Drill - and right now, thats copilot/gpt-4. If you don't want to be tied to a company and like opensource, feel free to connect a toy motor to an AA battery to drill your holes... Or to use Llama/Stable Code 3B.

You clearly have never used these other tools. Mixtral / Deepseek perform very well on coding challenges. I've used them against local code without issues, sometimes they are a bit optimistic and produce too much, but thats far better than producing too little (like GPT4 does).

Re: Stable Code 3B: Coding on the Edge

#42

Post by irthomasthomas »

londons_explore wrote: post #19
lfkdev wrote: post #6

How is this compared to the current GitHub Copilot?

If you just want to get stuff done, use the best tools like a Milwaukee Drill - and right now, thats copilot/gpt-4. If you don't want to be tied to a company and like opensource, feel free to connect a toy motor to an AA battery to drill your holes... Or to use Llama/Stable Code 3B.

Openai just invisibly dropped my API requests to a lower model with a 4k context limit. And my commit scripts started failing for being over the context limit. It's buried in the docs somewhere that low tier api users will be served on lower models during peek times.

So,I guess they're like a Milwaukee Drill that will sometimes refuse to work unless you buy more drill credits.

Re: Stable Code 3B: Coding on the Edge

#44

Post by a_wild_dandan »

tarruda wrote: post #10

Note that they don't compare with deepseek coder 6.7b, which is vastly superior to much bigger coding models. Surpassing codellama 7b is not that big of a deal today. The most impressive thing about these results is how good the 1.3B deepseek coder is.

This is phenomenal. And runs fast! The 33b version might be my MacBook's new coding daily driver.

Re: Stable Code 3B: Coding on the Edge

#45

Post by nulld3v »

irthomasthomas wrote: post #42
londons_explore wrote: post #19

Earlier quoted context omitted.

If you just want to get stuff done, use the best tools like a Milwaukee Drill - and right now, thats copilot/gpt-4. If you don't want to be tied to a company and like opensource, feel free to connect a toy motor to an AA battery to drill your holes... Or to use Llama/Stable Code 3B.

Openai just invisibly dropped my API requests to a lower model with a 4k context limit. And my commit scripts started failing for being over the context limit. It's buried in the docs somewhere that low tier api users will be served on lower models during peek times. So,I guess they're like a Milwaukee Drill that will sometimes refuse to work unless you buy more drill credits.

WTF? Do you have a link? I was not aware of this, it would be crazy if true.

Re: Stable Code 3B: Coding on the Edge

#47

Post by drzaiusx11 »

irthomasthomas wrote: post #42
londons_explore wrote: post #19

Earlier quoted context omitted.

If you just want to get stuff done, use the best tools like a Milwaukee Drill - and right now, thats copilot/gpt-4. If you don't want to be tied to a company and like opensource, feel free to connect a toy motor to an AA battery to drill your holes... Or to use Llama/Stable Code 3B.

Openai just invisibly dropped my API requests to a lower model with a 4k context limit. And my commit scripts started failing for being over the context limit. It's buried in the docs somewhere that low tier api users will be served on lower models during peek times. So,I guess they're like a Milwaukee Drill that will sometimes refuse to work unless you buy more drill credits.

More like a Milwaukee drill you have on loan that can be swapped out for a manual screwdriver without warning.

Re: Stable Code 3B: Coding on the Edge

#48

Post by manmal »

joshmarlow wrote: post #17
keyle wrote: post #2

That is fantastic. I'm building a small macOS SwiftUI client with llama cpp built in, no server-client model, and it's already so useful with models like openhermes chat 7B, and fast. If this opens it to smaller laptops, wow! We truly live in crazy time. The rate of improvement in this field is off the walls.

Not sure if this is where your head is, but I think there's a lot of value in integrating LLMs directly into complex software. Jira, Salesforce, maybe K8s - should all have an integrated LLMs that can walk you through how to perform a nuanced task in the software.

Imagine good error messages, with hints for mitigation and maybe smart retry w/ mitigations applied.

Re: Stable Code 3B: Coding on the Edge

#49

Post by devindotcom »

jjtheblunt wrote: post #46

Jargon naivete question: isn't "on the edge" normally implying on a server side with minimal routers hops to the client, not on client side?

afaik "edge" nearly always means taking place on the device a user is interacting with. no server involved except perhaps as authentication etc. but there is probably some other situation where "edge" could mean local infra or caching.

Re: Stable Code 3B: Coding on the Edge

#50

Post by jyap »

tarruda wrote: post #10

Note that they don't compare with deepseek coder 6.7b, which is vastly superior to much bigger coding models. Surpassing codellama 7b is not that big of a deal today. The most impressive thing about these results is how good the 1.3B deepseek coder is.

Deepseek Coder Instruct 6.7b has been my local LLM (M1 series MBP) for a while now and that was my first thought… They selectively chose benchmark results to look impressive (which is typical).

I tested out StableLM Zephyr 3B when that came out and it was extremely underwhelming/unusable.

Based on this, Stable Code 3B doesn’t look to be worth trying out. Guessing if they could put out a 7B model which beat Deepseek Coder 6.7B they would have.

Post reply on HN