taytus

>is a clone of grokbot really that interesting?

No.

Alternative title: Starting today, OpenAI is cutting its plan usage in half.

I wish more people could read and appreciate that couple of sentences.

>Who actually wants this?

Investors

oh well, if it is working for you, then we are saved.

Hopefully, a reset is coming.

Every 3 months*

This was my first thought as well. I can read online review about a product but I rather ask my friends their experience with it. Same thing here.

You don’t know what sol means? You don’t understand the difference in sizes between Terra and sol? I’m genuinely asking.

Lucky you! I'm considering switching from Kimi 2.7. What's your experience so far?

Anthropic is the most idiotic corporation in America, right now.

Roughly on par with GLM 5.2 at 5x the price

It's missing u

This is a good point I never thought of. I appreciate it.

At current prices, and considering these OS Models' performance, investing in local inference sounds like a bad idea.

I think it's the opposite. Who would want to buy shares in a company that's been flagged as a supply chain risk?

Incremental gains compounds.

Signaling.

Nice Fiction story.

Kimi feels almost limitless. I have the $40/month plan and I've never ever remotely close to hitting the limit. Using opus as the orchestrator.

Skills are not like hooks. Skills can and will inevitably be ignored.

Hooks are hard stops. In theory the model must respect them, unlike Claude.md or agents.md so yeah, it helps a lot.

Yes an no. Some skills are very very tuned to our own workflows. The model providers may come up with some similar alternatives but not always. Also, sometimes you need a solution now and not in three months.

I don’t have the prompt at hand but basically I told Kimi (paraphrasing): I have these Claude code skills, and I know it uses different tool calls than you but read them and re-write them as your own tools.

I also created a mini framework so it can test that the skills are actually working after implementation.

Everything runs perfectly.

Straight from them, but I know other providers like io.net can be faster but I like to directly support the project.

I'd recommend Kimi k2.6 for your use. It is an excellent model at a fraction of the cost, and you can use Claude Code with it.

I did a 1:1 map of all my Claude Code skills, and it feels like I never left Opus.

Super happy with the results.

>I asked DS itself and it denied this

Bro, seriously?

“after evals and dogfooding” couldn’t have done this before releasing the model? We are paying $200/month to beta test the software for you.

They should do a similar report about their communication team. This was horrible mismanaged.

Anthropic is making the exact same mistake OpenAI did: lack of focus. Release, release, release, all good apps, all full of bugs. This is a massive mess and people aren't talking enough about how bad all of this is.