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

Moonshot AI suspends new subscriptions due to Kimi K3 demand

twitter.com

Post reply on HN
Print view View original

91–100 of 118 posts

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#91

Post by kasey_junk »

ryandrake wrote: post #89
kasey_junk wrote: post #83

Earlier quoted context omitted.

Pretty straight ahead coding workflows. Most of my operational workflows are much simpler (because diagnosing an operational issue is much more time sensitive obviously).

As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time.

The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.

This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#92

Post by phyzix5761 »

thevinter wrote: post #15

Personal anecdote: I exhausted my Claude usage yesterday so I decided to spend 20$ to try Kimi while I was at it. Logged in, paid, downloaded Kimi Code, set it to use K3 and prompted something along the lines of: "Check this repository and find all the settings that can be passed as input related to hardware, I/O, thread control or networking. Produce a report". It thought for about 12 minutes and then told me I had…

I had the same experience with Claude the other day. I asked it for something fairly simple and it used up my whole 5 hour quota without producing the answer. Felt like a total waste of time.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#93

Post by noisy_boy »

Damn some timing, I just signed up few hours ago and within 3-4 hours spent over 50 bucks on my personal project (didn't realize that the launcher script I copied from an example had set effort to max). This is API use that consumes from your recharge amount. It found tons of issues with the code generated by Sonnet 4.6 (yeah I know, older model). Also didn't seem to burn through context window that fast (1M). The generated code works but quality could be better. Works fine with Claude code cli. The standout aspect was strong analytical abilities and a much more sobering and cautious tone (which is a good thing).

Will have to watch cost carefully though. If only I could get it at DeepSeek adjacent prices.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#94

Post by meowface »

noisy_boy wrote: post #93

Damn some timing, I just signed up few hours ago and within 3-4 hours spent over 50 bucks on my personal project (didn't realize that the launcher script I copied from an example had set effort to max). This is API use that consumes from your recharge amount. It found tons of issues with the code generated by Sonnet 4.6 (yeah I know, older model). Also didn't seem to burn through context window that fast (1M). The ge…

No offense but that seems like a...not good use of money. For the $100/month or $200/month tier you'd get way more out of Claude Fable 5, which is definitely a better model than K3 for coding.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#95

Post by noisy_boy »

meowface wrote: post #94
noisy_boy wrote: post #93

Damn some timing, I just signed up few hours ago and within 3-4 hours spent over 50 bucks on my personal project (didn't realize that the launcher script I copied from an example had set effort to max). This is API use that consumes from your recharge amount. It found tons of issues with the code generated by Sonnet 4.6 (yeah I know, older model). Also didn't seem to burn through context window that fast (1M). The ge…

No offense but that seems like a...not good use of money. For the $100/month or $200/month tier you'd get way more out of Claude Fable 5, which is definitely a better model than K3 for coding.

I fully agree. This isn't my usual pattern. I have a Claude pro subscription + some money loaded into DeepSeek which is super cheap. Just wanted to try out Kimi K3 and sort of got into the flow with the personal project. I am definitely not going to be burning more cash on this once the current recharge amount runs out.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#96

Post by ryandrake »

kasey_junk wrote: post #91
ryandrake wrote: post #89

Earlier quoted context omitted.

As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time.

The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode. This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.

I think this is an area where the developers of the agent harnesses should be spending a lot of effort. It's not reasonable to expect your users to set up and maintain a VM just to safely use a tool. When I run cmake, I don't have to worry about it accidentally deleting my root filesystem or posting my account credentials to github. Most of the command line coding tools I use don't even need/have a --dry-run option.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#97

Post by londons_explore »

gunalx wrote: post #38
JoshTriplett wrote: post #29

Earlier quoted context omitted.

> I always hated how the "Login" button is smaller on every website than the "Sign Up" button. I always assumed that was because it's the least common flow. Once you've signed up, you're logged in, so the only time you should ever need the "login" button is on a new computer, or after logging out to switch accounts, or if the service offers a "remember me" checkbox (don't do that) and doesn't check it by default ( de…

Your tokens should defiently have expiry times on the range that you would need to login again.

I would prefer a 999 year login cookie.

A well designed browser stores the cookies with similar security to the built in password manager anyway

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#98

Post by londons_explore »

kasey_junk wrote: post #91
ryandrake wrote: post #89

Earlier quoted context omitted.

As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time.

The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode. This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.

Frustratingly none of the coding harnesses seem to default to just firing up a docker container with the working directory mounted and letting the AI run wild inside the container.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#99

Post by kasey_junk »

ryandrake wrote: post #96
kasey_junk wrote: post #91

Earlier quoted context omitted.

The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode. This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.

I think this is an area where the developers of the agent harnesses should be spending a lot of effort. It's not reasonable to expect your users to set up and maintain a VM just to safely use a tool. When I run cmake, I don't have to worry about it accidentally deleting my root filesystem or posting my account credentials to github. Most of the command line coding tools I use don't even need/have a --dry-run option.

Could be. But a) I don’t know why I’d trust them to do that when existing tooling means I don’t have to and b) this is not a new paradigm for me. I’ve been running most of my dev environments in sandboxed mode for a long time. I don’t trust npm either.

Re: Moonshot AI suspends new subscriptions due to Kimi K3 demand

#100

Post by kasey_junk »

londons_explore wrote: post #98
kasey_junk wrote: post #91

Earlier quoted context omitted.

The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode. This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.

Frustratingly none of the coding harnesses seem to default to just firing up a docker container with the working directory mounted and letting the AI run wild inside the container.

You can get that working for yourself trivially. My agent environment now has 3 different kinds of compute abstractions, 3 different agents and a nascent workflow engine in it.

It works how _i_ want, which is really refreshing.

Post reply on HN