zlacker

Concur. GPT4 is like having an infinite-energy L3 engineer reporting to me. That's worth $10,000 per month according to the labor market. Sam has been giving away the farm!

>>kridsd+(OP)
People overestimating LLMs like this terrifies me so much

>>kridsd+(OP)
lol. This is like the HN opposite of the infamous dropbox post.

>>kridsd+(OP)
L3 engineer is a net negative bro.

>>nightf+Y6
I'd upgrade the parent comment to l4 with broad experience in every single open source tool in existence.

Historically, I'm a backend and distributed systems engineer, but integrating GPT4 into my workflows has unlocked an awe-inspiring ability to lay down fat beads of UI-heavy code in both professional and personal contexts.

But it's still an L3: gotta ask the right questions and doubt every line it produces until it compiles and the tests pass.

>>nightf+Y6
I had this disagreement with people on this site just the other day. People basically were like "you're asking it too complicated questions", but my response was then why does everyone make statements like the commenter you replied to?

>>nightf+Y6
Why?

>>nightf+Y6
It’s wild, I actually downgraded back to gpt 3.5 cuz gpt 4 just wasn’t worth the money.

>>bmitc+an
Because 99.9% of people who say things like this are just using ChatGPT itself and not any of the various awe-inspiring tools with full access to your codebase dynamically inserted into context via RAG. I have yet to talk to anyone who has actually worked for any amount of time against the GPT4 API or through Cursor, say, who underestimates their capabilities. Sincerely hoping this 'coup' doesn't mean the beginning of the end of that experience for most...

>>agentc+4q
> who underestimates their capabilities

Did you happen to mean overestimates? Just trying to make sure I understand.

>>agentc+4q
Context is very important in these kinds of use cases. If you work with something niche, I think these tools are less valuable because the training data becomes sparse.

For example, GPT-4 produces Javascript code far better than it produces Clojure code. Often, when it comes to Clojure, GPT-4 produces broken examples, contradictory explanations, or even circular reasoning.

>>bmitc+Mt
I just mean people who have actually used the API directly or through task-specific applications like Cursor that are meant to maximize use of AI for their needs know how much of a breakthrough we’ve had this year. People who doubt or downplay the already existing capabilities of this technology tend to have just played with ChatGPT a little bit (or have whatever ideological or other reason to do so).

>>janeta+lz
Have you tried Cursor out of curiosity? No ties to the company and long-time dev (Scala mostly), just genuinely found it to be transformative to my development practice like no tool before.