61–70 of 322 posts
It shocks me when people say that LLMs don't make them more productive, because my experience has been the complete opposite, especially with Claude Code. Either I'm worse than then at programming, to the point that I find an LLM useful and they don't, or they don't know how to use LLMs for coding.
The best part about llm coding is that you feel productive even when you aren't, makes coding a lot more fun.
I think it’s just that the base model is good at real world coding tasks - as opposed to the types of coding tasks in the common benchmarks. If you use GitHub Copilot - which has its own system level prompts - you can hotswap between models, and Claude outperforms OpenAI’s and Google’s models by such a large margin that the others are functionally useless in comparison.
Earlier quoted context omitted.
It depends very much on your use case, language popularity, experience coding, and the size of your project. If you work on a large, legacy code base in COBOL, it's going to be much harder than working on a toy greenfield application in React. If your prior knowledge writing code is minimal, the more amazing the results will seem, and vice-versa. Despite the persistent memes here and elsewhere, it doesn't depend very…
Overall I would agree with you, but I start feeling that this „iron law“ isn’t as simple as that. After all, humans have limited „context window“ too — we don’t remember every small detail on a large project we have been working on for several years. Loose coupling and modularity helps us and can help LLM to make the size of the task manageable if you don’t ask it to rebuild the whole thing. It’s not the size that ma…
(Though now that I think of it, I might start interrupting people with “SUMMARIZING CONVERSATION HISTORY!” whenever they begin to bore me. Then I can change the subject.)
Oof, this comes at a hard moment in my Claude Code usage. I'm trying to have it help me debug some Elastic issues on Security Onion but after a few minutes it spits out a zillion lines of obfuscated JS and says: Error: kill EPERM at process.kill (node:internal/process/per_thread:226:13) at Ba2 (file:///usr/local/lib/node_modules/@anthropic-ai/claude-code/cli.js:506:19791) at file:///usr/local/lib/node_modules/@anthro…
We’re considering building a coding agent for Lowdefy[1], a framework that lets you build web apps with YAML config. For those who’ve built coding agents: do you think LLMs are better suited for generating structured config vs. raw code? My theory is that agents producing valid YAML/JSON schemas could be more reliable than code generation. The output is constrained, easier to validate, and when it breaks, you can act…
This is essential to productivity for humans and LLMs alike. The more reliable your edit/test loop, the better your results will be. It doesn't matter if it's compiling code, validating yaml, or anything else.
To your broader question. People have been trying to crack the low-code nut for ages. I don't think it's solvable. Either you make something overly restrictive, or you are inventing a very bad programming language which is doomed to fail because professional coders will never use it.
We’re considering building a coding agent for Lowdefy[1], a framework that lets you build web apps with YAML config. For those who’ve built coding agents: do you think LLMs are better suited for generating structured config vs. raw code? My theory is that agents producing valid YAML/JSON schemas could be more reliable than code generation. The output is constrained, easier to validate, and when it breaks, you can act…
How do you specify callbacks? Config files should be mature programming languages, not Yaml/Json files.
Might sound crazy but we built full web apps in just yaml.. Been doing this for about 5 years now and it helps us scale to build many web apps, fast, that are easy to maintain. We at Resonancy[1] have found many benefits in doing so. I should write more about this.
[1] - https://resonancy.io
What do people think of Google's Gemini (Pro?) compared to Claude for code? I really like a lot of what Google produces, but they can't seem to keep a product that they don't shut down and they can be pretty ham-fisted, both with corporate control (Chrome and corrupt practices) and censorship
It shocks me when people say that LLMs don't make them more productive, because my experience has been the complete opposite, especially with Claude Code. Either I'm worse than then at programming, to the point that I find an LLM useful and they don't, or they don't know how to use LLMs for coding.
First of all, keep in mind that research has shown that people generally overestimate the productivity gains of LLM coding assistance. Even when using a coding assistant makes them less productive, they feel like they are more productive.
Second, yeah, experience matters, both with programming and LLM coding assistants. The better you are, the less helpful the coding assistant will be, it can take less work to just write what you want than convince an LLM to do it.
Third, some people are more sensitive to the kind of errors or style that LLMs tend to use. I frequently can't stand the output of LLMs, even if it technically works; it doesn't live to to my personal standards.