why is Anthropic extending the retirement date for Sonnet 3.5

Tried cursor new model composer 1 to fix an issue, it fast but failed to solve it after few tries. GPT 5 Codex fixed it in one shot.

Thank you Anthropic, will try it again.

While I respect VS Visual Studio Code, but it really falls behind Cursor, not just features even the performance is still inefficient. I think we can't mock Cursor for just a VS Code fork, they really bring innovations on top of VS Code.

This is interesting if we take a look from the business perspective rather than engineering perspective. The secret of successful product is not determined by the code quality, but rather by how well the product really solves the user's problems.

Windsurf new model SWE-1.5 and Cursor new model Composer 1 should trigger innovations for big lab like OpenAI and Anthropic to deliver SOTA fast frontier models for coding.

I think this is one of the best YC talk i've watched so far. It teaches you how to see the world from an entrepreneurial perspective. Great talk Jake Heller youtube.com/watch?v=l0h3nA…

The current slowness of model inference is like internet speed when it first started, it was slow at the beginning and eventually a fast internet speed would become the new standard. I think this applies the same with model inference speed right now.

$1,000 free usage credits from Claude for max plan users🚀

Claude 4.5 is pretty good at UI Design. But you need to provide guidance and initial styling. The rest Claude will figure it out on the fly. Instead of asking to make it to be more modern or beautiful which ended up with purple gradients all over the place.

this is how you know if Claude has been there

Using Codex after using Claude 4.5 Sonnet feels really slow.

I am using both Claude Code and Codex CLI, but Claude Code UI/UX is better than Codex.

Pro tip: If you have tried several times to fix a bug/issue with AI and it doesn't work, it's not always the model is bad. Maybe the context window has been bloated too much, try to clear or start new conversation. Surprisingly it may work! If it's not then try with other model.

Finally Opus 4.5 is out, tried it and it looks very solid.

From my experience Claude Sonnet 4.5 Thinking is still > Gemini 3 Pro. It is good for debugging, and Claude models are also nicer to talk with. Great job Anthropic

Gemini 3 Flash on Google Antigravity is really good! It feels like Sonnet 4.5 and one-shotted UI related task most of the time.

a casual chat with gemini, i like this line: sometimes "good enough" is better than "perfect.". -- keep the bar high, but understand the trade offs for every perfections you want to accomplish.

I think the future of SWE might look like managing multiple different coding agents instead of writing the code by yourself, natural language would be the main language. And having a great technical knowledge fundamentals still puts you in a better leverage.

If AI already so good at building native mobile apps, do we still need react native?