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

101–110 of 201 posts

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

#101

Post by Vinnl »

acpdev wrote: post #44
Vinnl wrote: post #36

Earlier quoted context omitted.

So if you use Claude via Copilot in Zed... You use Zed's harness, I think? What does Copilot do, at that point?

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?

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

#102

Post by phillipcarter »

ffsm8 wrote: post #60
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…

> they should have waited until the competition changed their prices first. They did... They're literally just passing on the costs https://platform.claude.com/docs/en/about-claude/pricing Anthropic just provides a subscription - which Enterprise usually doesn't want you to use because everything you're submitting through that will be trained on / becomes part of their model. So If you use it without explicit permiss…

It's a little more complicated than that, unfortunately.

If you use Claude via API in your own app, you're paying full price.

If you have an "API Plan" for Claude Code (i.e., free), you're paying full price.

If you have a Pro, Max, Max 5x, or Max 20x, your tokens are subsidized up until a rate limit. Then you pay full price for usage thereafter, until the end of the billing cycle.

The widespread belief in industry right now is that the per-seat pricing (which Copilot bailed from first) is going to go away in the near-term.

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

#103

Post by blensor »

JSR_FDED wrote: post #100
blensor wrote: post #71

Earlier quoted context omitted.

I am curious if you implicitly assumed they are Macs or if that's what you are looking for specifically?

I assumed the 27B dense model would be preferable to a MoE model, and that it wouldn’t fit into a consumer graphics card, which leaves the Macs. Then I assumed for cost and battery/heat reasons that a Mini would be better than a laptop.

The reason why I was curious is that I am running my stuff on a Strix Halo and I get the feeling that this class of devices ( gmktek, minisforum, lenovo, etc. ) seem to becoming a pretty good alternative

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

#104

Post by lanthissa »

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…

i ran out of claude credits for the first time at work in months and had to fallback to copilot.

pleasantly surprised, claude's way ahead in tooling but the ability to designate what model your subagents use and having access to all models is a better feature than all of what claude offers combine atm.

The only limit on the amount of ai can consume in a month a work is dollars, so anything that helps with cost is the best model/harness for me.

It also did a better job at smart designating subagents itself where as claude often used higher cost models.

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

#105

Post by cyanydeez »

ACCount37 wrote: post #84
cyanydeez wrote: post #74

Earlier quoted context omitted.

I never got into any of the AI models because it was clear local first was going to be more valueable, if they were to replace coding tasks. I tried out a few models and ended up going with either Qwen3-Coder-Next (no think, just do) and Qwen3.6-35B (thinking, w/llamacpp token budget). Created a customized prompt that works fairly well to around ~60k tokens and then is a toss up on whether it's poisoned itself or I'v…

We live in a non-deterministic world. Anything "deterministic" in it is a castle built on quicksand. LLMs are, as far as the nastiness of the Real World goes, really fucking benign. Future models outperform past models, both in open weight land and at the big frontier labs. Performance per $ only ever goes up. That's just nice.

YES, but you seem to not understand that having two non-deterministic layers is incompatible. #1 is fine: it has random issue and you build around those random issues; those issues don't change unless you change them.

#2 is not fine; that non-determinism you do not control, have no insight into, etc.

I'm saying sure, give me #1 if it means I can build a harness around it and smooth over the edges. But I'm not taking #1 and #2. There's zero reasonable way to manae two non-deterministic systems.

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

#106

Post by cyanydeez »

cogman10 wrote: post #85
maykthewessen wrote: post #77

Earlier quoted context omitted.

Qwen is the Alibaba distilled Anthropic Claude model So piracy on an by piracy trained ai model..

Piracy? Lol. Alibaba didn't steal Opus weights, they used opus output to train their model. If this is piracy, then so is reverse engineering efforts powering a bunch of Linux drivers.

If that's piracy, I'm going to the library and arresting everyone there!

Also, yeah, they already stole their copyrighted works, so a thief from a thief is still...theives?

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

#107

Post by ofjcihen »

Incipient wrote: post #50
nsbk wrote: post #49

Earlier quoted context omitted.

The price hike was insane. My $dayjob is moving away from Copilot and into Claude Code subscriptions. In parallel we are testing AWS bedrock and Deepinfra for open weight models in preparation for when CC inevitably stops being such a good deal and aligns with actual token cost. Fun times.

I had to do the same. I expect everything will go token pricing, and at that point a LOT of small/mid businesses will drastically change how they use code. I've swapped to the 20x Claude plan for a month or two to knock out two ideas I need to get it MVP - expecting Claude to go token priced soon.

Hell it’s past small and mid. I do work for a few of the fortune 100s and what I’m hearing is somewhere between “justify all of your usage or don’t use it” to “you now get 500 bucks a month, go over that and you’re getting it revoked”

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

#108

Post by rpdillon »

credit_guy wrote: post #90
andhuman wrote: post #4

Finally an alternative to the big dogs that a company can use. People have been asking for a way to run the Chinese models from a trusted provider. Here GitHub delivered! The performance, if we trust the benchmarks, put it at Sonnet 4.6. Let’s see if it’s worth it with GitHubs pricing.

> The performance, if we trust the benchmarks, put it at Sonnet 4.6. I don't trust these benchmarks. I used a number of times Kimi K2.7 and I was disappointed. It would run in circles for things that Claude would do in one shot. However, my usage was via Ollama cloud, and I have no idea if they serve the actual model or a quantized version, and it was the quantization that degraded the performance. The great news, in…

Check your harness. I use Kimi K2.6 for a lot of stuff with OpenCode and omp and it's extremely effective. I'm gonna try 2.7, but it should be capable model based on what I've seen with previous models.

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

#109

Post by ffsm8 »

phillipcarter wrote: post #102
ffsm8 wrote: post #60

Earlier quoted context omitted.

> they should have waited until the competition changed their prices first. They did... They're literally just passing on the costs https://platform.claude.com/docs/en/about-claude/pricing Anthropic just provides a subscription - which Enterprise usually doesn't want you to use because everything you're submitting through that will be trained on / becomes part of their model. So If you use it without explicit permiss…

It's a little more complicated than that, unfortunately. If you use Claude via API in your own app, you're paying full price. If you have an "API Plan" for Claude Code (i.e., free), you're paying full price. If you have a Pro, Max, Max 5x, or Max 20x, your tokens are subsidized up until a rate limit. Then you pay full price for usage thereafter, until the end of the billing cycle. The widespread belief in industry ri…

It's not more complicated? I referenced the subscription... I just added a small warning about it as some people may or may not be aware about the fact they're opening themselves up to serious consequences if they decide to use it on their employers code without explicit permission... Depending on their employers digression, eg largish entrenched employers which value their IP will be more willing to inflict damages on you. An upstart will likely not care unless the CEO sees an opportunity to profit personally.
Post reply on HN