Second, you might want to customize your code in ways that aren’t straightforward for ChatGPT to guess.
You might say, “Actually, I don’t want to just greet the user, I want to greet them in a rotating set of five languages, randomly chosen.”
That’s the kind of problem-solving
CODE
-
Customizing ChatGPT Code with Rotating Language Greetings
By
–
-
ChatGPT Limitations: Catching Errors in AI Code Suggestions
By
–
First, ChatGPT isn’t perfect. It’s a brilliant tool, but it can make mistakes or misinterpret your instructions.
You need to be able to catch errors, reason about your code, and figure out how to fix it when ChatGPT’s suggestions don’t work as planned. -
Why Learning Programming Remains Essential With ChatGPT
By
–
One question I get a lot is: "if ChatGPT can just write code for me, do I even need to learn how to program? " The answer is undeniably yes, for a few reasons…
-
Integration of new AI feature into core codebase
By
–
We did a blog post demoing an example of it, but it's the first release that makes it part of the core code (contributed by @merve
) -
How to install and set up smolagents for AI agents
By
–
pip install smolagents
And add [dev] to get the whole stuff! -
Diffs Auto-Close Feature Reduces Workspace Clutter
By
–
We've de-cluttered diffs.
— Replit ⠕ (@Replit) 1 février 2025
Assistant diffs now auto-close when they're applied, so you'll have fewer unused tabs in the workspace. pic.twitter.com/nwBzdSgMuxWe've de-cluttered diffs. Assistant diffs now auto-close when they're applied, so you'll have fewer unused tabs in the workspace.
-
DeepSeek-V3 vs Qwen2.5: coding quality comparison
By
–
5/ Coding
— God of Prompt (@godofprompt) 1 février 2025
• DeepSeek-V3: Well-structured code with advanced features.
• Qwen2.5: Simpler code and was easy to navigate and work with
Winner: DeepSeek-V3 and Qwen (3-2) pic.twitter.com/jScwpCyGzx5/ Coding • DeepSeek-V3: Well-structured code with advanced features.
• Qwen2.5: Simpler code and was easy to navigate and work with Winner: DeepSeek-V3 and Qwen (3-2) -
OpenAI o3-mini Surpasses o1-mini in Codeforces Competitive Programming
By
–
On Codeforces competitive programming, @OpenAI o3-mini achieves progressively higher Elo scores with increased reasoning effort, all outperforming o1-mini. With medium reasoning effort, it matches o1’s performance.
-
Optimizing AI Reasoning with Shorthand Chain of Thought Language
By
–
I asked o3 on how I’d optimize this for faster reasoning and one of the ideas it gave me was to invent a shorthand language for the chain of thought to guzzle less tokens https://
gist.github.com/willccbb/46767
55236bb08cab5f4e54a0475d6fb
…