valentinconan

I agree with this opinion

It seems to work for me when I select the model "/model claude-sonnet-4-5-20250929" . Here the list of all model and the retirement date https://platform.claude.com/docs/en/about-claude/model-depre.... Hope it helps

> Kids these days... Haha, if that makes me a bit younger, I’ll take it :)

I agree, that happens a lot with PayPal, unfortunately :(

This is the first time I've heard about this from Stripe, but basically, when they issue a refund, Stripe needs to generate a “refund invoice” that proves the refund was processed. If you have access to your account, just download it; otherwise, if you can't access your account, ask them to send you these “refund invoices.” Once you have this document, you’ll be able to prove to your customer that the refund was processed.

So create a new invoice and use a different payment system.

I had this website in my bookmarks https://www.goeuropean.org/, but I'm not sure if it's up to date. If that helps...

I used to use Gemini CLI and was pretty happy with it… until I started using Claude Code. I think it’s, for now, the most advanced AI tool available right now. You can manage skills, the MCP, plugins, agents, hooks… It’s a truly comprehensive tool, but its main drawback is the token consumption of the Anthropic model, especially in recent days. There are solutions to reduce input tokens, for example this GitHub project https://github.com/rtk-ai/rtk. It uses hooks to replace certain commands with optimized ones and helps reduce the number of input tokens. It’s a start...

Nice work ! Did you plan to run tests with Opus 4.6 using Max reasoning ? I'm curious to see if there's really a difference compared to “High” mode.

I haven't yet tried to solve truly complex algorithmic problems.

Generally speaking, if the problem is common, the model has likely already been trained to solve it.

If it's truly complex and/or specific to my needs, I can try using a reasoning model to think through a solution before moving on to implementation.

I use the agent to conduct research, find resources to understand the complexity, best practices, feedback, etc., and to write a Markdown analysis file on the topic.

Then I can use this file as a basis to precisely define what I want to do and brainstorm with the agent in thinking mode. The more the task is described and defined, the more accurate the result will be.

In my opinion, AI agents are currently just as capable as novice developers. Their main advantage is that they’re much faster than we are when the task involves generating a lot of code.

If the task is simple, I spend more time telling it what to do than doing it myself. But if the task is complex, I use certain skills/commands and create intermediate files (more than necessary) between each step (analysis, planning, design, workflow, and implementation) and clear the context between each of them. The result is fairly accurate, but not perfect.

My take is, we remain the architects of our code, and AI agents are an excellent tool that we need to master.

There are no details about the cause of the error, but it has been happening more often since they doubled the tokens until March 27

Great, I'll update it. Thanks

Great, thanks for sharing :)