Claude Code + GLM-4.6—really impressive!
— 机器之心 JIQIZHIXIN (@jiqizhixin) 30 septembre 2025
Thank you, @AnthropicAI and @Zai_org pic.twitter.com/2fzt2IffAc
Claude Code + GLM-4.6—really impressive! Thank you, @AnthropicAI and @Zai_org
By
–
Claude Code + GLM-4.6—really impressive!
— 机器之心 JIQIZHIXIN (@jiqizhixin) 30 septembre 2025
Thank you, @AnthropicAI and @Zai_org pic.twitter.com/2fzt2IffAc
Claude Code + GLM-4.6—really impressive! Thank you, @AnthropicAI and @Zai_org
By
–
it can do php app too ? because most if the time it's bad for seo.

By
–
Claude annonce Sonnet 4.5, présenté comme le meilleur modèle de code au monde. Du moins, sur les benchmarks… On attend de voir. Mais connaissant Claude, ça ne paraît pas déconnant.
By
–
Here's the instructions for trying it: https://
support.microsoft.com/en-us/office/a
gent-mode-in-excel-frontier-a2fd6fe4-97ac-416b-b89a-22f4d1357c7a
…
By
–
Is there a better prompt which tells them not to overthink and keep it simple? They just bombard my code base with test cases, unnecessary documentation, print statements.

By
–
Seoul National University & Adobe Present: Program Synthesis via Test-Time Transduction A formulation that explicitly leverages test inputs during synthesis, unlike prior approaches that only generalize from training examples. Key idea: treat synthesis as active learning over a

By
–
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs The Chinese University of Hong Kong, Shenzhen, and others
Paper: https://
alphaxiv.org/abs/2509.17998
v2
…
Code: https://
github.com/richardcsuwand
i/cake
…

By
–
Anthropic just launched Claude 4.5 Sonnet, Agents SDK with Claude Code 2.0 directly in VS Code.
— Shubham Saboo (@Saboo_Shubham_) 30 septembre 2025
Is Claude Code slowly replacing Cursor?? pic.twitter.com/Maj7vgEIPk
Anthropic just launched Claude 4.5 Sonnet, Agents SDK with Claude Code 2.0 directly in VS Code. Is Claude Code slowly replacing Cursor??
By
–
Yes! It basically picks up where the LLM from Scratch left of. I.e., we start with a pre-training LLM and then implement and add reasoning techniques.
(However, it can also be read as a standalone book)
By
–
Cursor's own telemetry might saw yes, but in Armin's case he's using Claude Code so his self-reported numbers aren't based on autocomplete features