I work on brain dead crud apps much of my time and get nothing from LLMs.
> This is actually amazing now, just use [insert ChatGPT, GPT-4, 4.5, 5, o1, o3, Deepseek, Claude 3.5, 3.9, Gemini 1, 1.5, 2, ...] it's completely different from Model(n-1) you've tried.
I'm not some mythical 140 IQ 10x developer and my work isn't exceptional so this shouldn't happen.
Tried about four others, and to some extent I always marveled about capabilities of latest and greatest I had to concede they didn’t make faster. I think Claude does.
That poster isn't comparing models, he's comparing Claude Code to Cline (two agentic coding tools), both using Claude Sonnet 4. I was pretty much in the same boat all year as well; using Cline heavily at work ($1k+/month token spend) and I was sold on it over Claude Code, although I've just recently made the switch, as Claude Code has a VSCode extension now. Whichever agentic tooling you use (Cline, CC, Cursor, Aider, etc.) is still a matter of debate, but the underlying model (Sonnet/Opus) seems to be unanimously agreed on as being in a league of its own, and has been since 3.5 released last year.
Because of the absolute dearth of high-quality open-source driver code and the huge proliferation of absolutely bottom-barrel general-purpose C and C++, the result is... Not good.
On the other hand, I asked Claude to convert an existing, short-ish Bash script to idiomatic PowerShell with proper cmdlet-style argument parsing, and it returned a decent result that I barely had to modify or iterate on. I was quite impressed.
Garbage in, garbage out. I'm not altogether dismissive of AI and LLMs but it is really necessary to know where and what their limits are.