Claude Opus 4.5 was released in November of 2025, and for coding it was a real game-changer. If your impression of AI coding tools was formed on the models that came before it, I'd gently suggest it's worth a fresh look. The ground has moved more than most people realize.
The field moves fast enough that a year-old impression is genuinely out of date. Judging today's tools by a model from a generation ago is a bit like judging a craft by the first rough prototype you tried, fair at the time, but no longer the whole picture.
A lot of the skeptical engineers I know formed their view on those earlier models, and I understand why, the experience was often frustrating. But the tools they tried aren't the tools we have now, and that's worth considering before writing the whole approach off.
And if you've used Claude Code since the 4.5 release and still come away underwhelmed, it might be worth revisiting how you're prompting it. That isn't a dig. "Prompt engineering" is a real thing, and there is genuine skill in framing a request so the model can do its best work.
Working with an LLM is a little like working with a chaotic system, in the mathematical sense, where the outcome is extremely sensitive to its initial conditions. The context and prompt you provide are those initial conditions, and small changes in them can lead you to very different results.
Here's an example to illustrate my point. When you enter a prompt (and any additional context files), the number of "possible correct answers" could be enormous. Consider the following prompt:
"Write me a script that resizes an image."
Compare that to this prompt:
"Write me a Python script that resizes an image."
By simply adding the word "Python" to our prompt, we help the LLM eliminate all possible correct solutions that don't include Python. Could the LLM technically write an image resizer in JavaScript? Sure, but now it knows that you want a Python script, so it can narrow its focus to Python-based solutions.
Think of it like a game of Guess Who. You ask your opponent, "Does your person have red hair?" No? Then you flip down all of the people with red hair, and the game goes on with you narrowing your options.
Here's one more prompt to drive the point home:
"Could you please write me a Python script that resizes an image? The script should support JPEG and PNG files as valid resizable image formats. The resulting resized image should be saved as a WEBP image. Please save the resized image in the same folder as the original image. Please do not overwrite the original image. The script should accept the image's path as a command line argument (ex: python3 ./resizer.py ~/path/to/images). The script should also support a --all flag. If the --all flag is passed, then the script should automatically resize all JPEG and PNG images found in the given folder path. The script should also accept a command line argument so the user can specify the desired resize resolution. Image aspect ratios should always be preserved. Please also provide a corresponding README.txt file that explains how to use the script. Does this all make sense?"
Now that's a prompt. Of the three prompts shown on this page, which do you think would yield the best result?
One follow-up note, I've found that framing my prompts as questions instead of commands yields much better results. LLMs tend to be sycophantic, so if you give it a direct order it will do its very best to oblige. I wouldn't be surprised if an overly-assertive tone in the context and prompts leads to a statistically higher number of hallucinations.
Ask, don't tell.