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

Kimi K2.7 Code is generally available in GitHub Copilot

github.blog

Post reply on HN
Print view View original

181–190 of 201 posts

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#181

Post by matteocontrini »

Kon5ole wrote: post #46

I am a huge fan of Copilot CLI. It just feels so logical and low-friction to use compared to Claude Code. Having the ability to juggle various models at will is really nice too. ("Plan this using Opus 4.6, let GPT 5.4 verify the plan and give feedback before implementing with Sonnet 4.6"). Unfortunately the June pricing change for Copilot forced me personally as well as my entire department at work to switch to Claud…

Copilot's main target is probably enterprises, who already pay per token with both Claude and Codex, on top of a per-seat subscription. With Copilot they get both Claude and Codex and many other models in one subscription. Also, per-seat price includes usage and the cost of extra usage is identical to going direct with model providers. I'd say it makes sense.

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#182

Post by acpdev »

Vinnl wrote: post #101
acpdev wrote: post #44

Earlier quoted context omitted.

I believe you are using https://github.com/github/copilot-cli or potentially this https://github.com/github/copilot-language-server-release#ag... via the Agent Client Protocol https://github.com/agentclientprotocol/agent-client-protocol which means you are indeed using Copilot's harness ACP is just a standard that bridges harnesses easily into IDEs, Text Editors, or whatever consumes it (I wrote a TUI that consumes t…

Ah OK, so the ACP connector ensures tool calls work with Zed, and communicates the available tools and their results to the harness, and then the harness mainly provides a system prompt and the API calls?

Harness does a lot of things potentially, but this depends on the harness.

1. Manages what is loaded in the context (I.e. sent to the model), this can be about compaction, summarization, removing things it judges no longer relevant, proving memory 2. Handling retries and how to resend data , lot of model specific behavior here 3. Wires up tools like web search or lsp servers 4. Skills and how to use them 5. Plugins/sdks 6. Management of rules (AGENTS.md)

About everything interesting really, a ton of work goes into this and getting it right is surprisingly hard

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#183

Post by purerandomness »

matrik wrote: post #94

And why should one prefer GitHub Copilot over OpenCode? Worse harness, more expensive prices, unreliable product strategy, limited model support, the list goes on.

You can select Copilot as provider in OpenCode.

Copilot is used a safe liability layer for enterprises, not as an actual harness.

At $OURCORP we are only allowed to use models available in Copilot. No problem to use them in OpenCode.

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#184

Post by tancop »

zaphirplane wrote: post #134
c7b wrote: post #128

Earlier quoted context omitted.

I'm not sure what you're trying to say. Is that a good or a bad thing? Model distillation is presumably part of the reason why Qwen is so good, yes. As a consumer, that's a good thing I would say. It's a natural counterbalance to the monopolistic tendencies of other tech segments. If you have ethical concerns, model distillation feels like an arbitrary line to draw. Why is the first type of piracy ok, the second not?…

Are you saying 2 wrongs make a right

in this case yes. stealing from a thief is right if you give all of it back to the victims. with ai the "stealing" is from everyone on the internet, so the only ethical option is making the results open source and available to all. thats exactly what chinese labs are doing.

(in general i think piracy or breaking ip laws in general is not morally wrong unless you make money from it, but thats a whole other conversation.)

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#185

Post by love0972 »

kamranjon wrote: post #144
c7b wrote: post #57

Gotta say, I've lost all interest in cloud-based AI products. Too many cool features and workflows that I was once excited about that I can't or don't use anymore for a variety of reasons (price hikes, subjectively nerfed, disappeared altogether, replaced,...) for me to even remember. It's tiring. I've set up a small rig, mostly settled on Qwen3.6 and I'm slowly adding features myself. It probably can't compete with…

I'm really happy this is one of the top comments here, I am fully local as well. Just wanted to leave a note for folks who might not have the memory to run a big 32gb model - I just found out there are some pruned models that have really good performance and If I had a smaller machine I might try this pruned unsloth Q4 quant of GLM 4.7 flash that sits at 14gb: https://huggingface.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B…

[flagged]

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#187

Post by MrDrMcCoy »

kamranjon wrote: post #144
c7b wrote: post #57

Gotta say, I've lost all interest in cloud-based AI products. Too many cool features and workflows that I was once excited about that I can't or don't use anymore for a variety of reasons (price hikes, subjectively nerfed, disappeared altogether, replaced,...) for me to even remember. It's tiring. I've set up a small rig, mostly settled on Qwen3.6 and I'm slowly adding features myself. It probably can't compete with…

I'm really happy this is one of the top comments here, I am fully local as well. Just wanted to leave a note for folks who might not have the memory to run a big 32gb model - I just found out there are some pruned models that have really good performance and If I had a smaller machine I might try this pruned unsloth Q4 quant of GLM 4.7 flash that sits at 14gb: https://huggingface.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B…

It's a good model for sure, but it's training set is based on some pretty old stuff. Would be good to post-train any languages / frameworks you care about being current into a LoRA for it. I even had to do that for the newer Qwen3.6, but it wasn't too hard thanks to Unsloth.

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#188

Post by MrDrMcCoy »

selectodude wrote: post #130
SV_BubbleTime wrote: post #129

Earlier quoted context omitted.

Understated how much of a boon for Linux that AI development has been. There isn’t any benefit to running a windows machine.

Au contraire, I run models on WSL and my desktop reliably wakes up from sleep. Best of both worlds.

Genuine question: what are the good parts of Windows that keep you there? I've been such a happy gamer/coder/media editor on Linux for so long that I really don't understand how Microsoft isn't dead yet.

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#189

Post by naveen99 »

pimeys wrote: post #126
organsnyder wrote: post #124

Earlier quoted context omitted.

The biggest appeal of the frontier models is for those trying to get autonomous agentic systems running that do real work with minimal human input. I went down a rabbit hole trying that with frontier models, and after a lot of initial promise it ended up actually slowing me down.

We've all been through that no? In the beginning you can do a ton of stuff without reading code. But the LLMs miss all the good abstractions, they just push and push unmaintainable code until at some point you start having more bugs and then you NEED that LLM to fix the codebase you don't understand anymore. There are guardrails you can and must add to protect your team if you take the vibe approach: a good type syst…

Just keep a good grip on the data. Code is easy to replace then.

Re: Kimi K2.7 Code is generally available in GitHub Copilot

#190

Post by SwellJoe »

pbgcp2026 wrote: post #178
SwellJoe wrote: post #157

Earlier quoted context omitted.

A 4-bit quantization of either Qwen 3.6 27b or Gemma 4 31b will run on a 32GB Mac with a decent-sized, but not full-sized, context. 64GB gets you the full ~256k context and you don't need to quantize your KV cache (though 8-bit quantization of KV may be worth it for performance). The 4-bit QAT version of Gemma 4 has practically identical performance to the full size version or the 8-bit version in most benchmarks and…

A 4-bit quantization is useless in real projects.

The Gemma 4 QAT 4-bit models are basically indistinguishable from the 8-bit or 16-bit versions. I tested, and many benchmarks agree. For models where there isn't a QAT version, 6-bit is where it starts to degrade, but only a little if using dynamic quantizations like unsloth provides.

When I use Qwen, I use the 8-bit quantization. But, when I use Gemma there is literally no reason to use anything other than the 4-bit QAT. It's faster, it's smaller, there's more room for context, and it performs at something like 99+% of the 16 bit.

Post reply on HN