161–170 of 281 posts
Earlier quoted context omitted.
I also genuinely hate using jq. It is one of the only things that I rely heavily on AI.
At that point why don't we ask the AI directly to filter through our data? The AI query language is much more powerful.
It's an important idea in computer science. Go and learn.
When initially opening the page it had broken colors in light mode. For anyone else encountering it: switch to dark mode and then back to light mode to fix it.
Earlier quoted context omitted.
Because the output you get can have hallucinations, which don’t happen with a deterministic tool. Furthermore, by getting the `jq` command you get something which is reusable, fast, offline, local, doesn’t send your data to a third-party, doesn’t waste a bunch of tokens, … Using an LLM to filter the data is worse in every metric.
You can use a local LLM and you can ask it to use tools so it is faster.
Jq's syntax is so arcane I can never remember it and always need to look up how to get a value from simple JSON.
Shameless plug, but you might like this: https://github.com/IvanIsCoding/celq jq is the CLI I like the most, but sometimes even I struggled to understand the queries I wrote in the past. celq uses a more familiar language (CEL)
Earlier quoted context omitted.
I also genuinely hate using jq. It is one of the only things that I rely heavily on AI.
At that point why don't we ask the AI directly to filter through our data? The AI query language is much more powerful.
Because the input might be huge.
Because there is a risk of getting hallucinations in the output.
Isn't this obvious?
Earlier quoted context omitted.
At that point why don't we ask the AI directly to filter through our data? The AI query language is much more powerful.
You really need to go and learn about the concept of determinism and why for some tasks we need and want deterministic solutions. It's an important idea in computer science. Go and learn.
Jq's syntax is so arcane I can never remember it and always need to look up how to get a value from simple JSON.
I also genuinely hate using jq. It is one of the only things that I rely heavily on AI.
Earlier quoted context omitted.
Because the output you get can have hallucinations, which don’t happen with a deterministic tool. Furthermore, by getting the `jq` command you get something which is reusable, fast, offline, local, doesn’t send your data to a third-party, doesn’t waste a bunch of tokens, … Using an LLM to filter the data is worse in every metric.
You can use a local LLM and you can ask it to use tools so it is faster.
Quick comment for the author. Just added this new tool to arkade, along with the existing jq/yq. No Arm64 for Darwin.. seriously? (Only x86_64 darwin.. it's a "choice") No Arm64 for Linux? For Rust tools it's trivial to add these. Do you think you can do that for the next release? https://github.com/micahkepe/jsongrep/releases/tag/v0.7.0