AI Coding

27 readers
1 users here now

A community to discuss agentic and AI assisted coding.

All users are expected to follow the code of conduct, particularly in regards to voting:

1.3. Vote for quality: When downvoting content in communities the downvotes should reflect the quality of the content rather than whether you personally agree with it.

founded 2 months ago
MODERATORS
codeinabox@programming.dev
listing: all - local
76
6
AI Makes the Easy Part Easier and the Hard Part Harder (www.blundergoat.com)
submitted 1 month ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/914277

Comments

77
1
On Programming with Agents (zed.dev)
submitted 1 month ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
78
2
AI fatigue Is real and nobody talks about it (siddhantkhare.com)
submitted 1 month ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

This is the paradox: AI reduces the cost of production but increases the cost of coordination, review, and decision-making. And those costs fall entirely on the human.

79
1
Circumstantial Complexity, LLMs and Large Scale Architecture (www.datagubbe.se)
submitted 1 month ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/912764

Comments

80
1
The Rise of Spec Driven Development (www.dbreunig.com)
submitted 1 month ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
81
1
Context Engineering for Coding Agents (martinfowler.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
82
1
Claude Code Swarms (addyosmani.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
83
1
My AI Adoption Journey (mitchellh.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/906555

Comments

84
2
The LLM spectrum and responsible LLM use (martin.janiczek.cz)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/906546

Comments

85
1
Agentic Proof-Oriented Programming (risemsr.github.io)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/906389

Comments

86
2
So yeah, I vibe-coded a log colorizer—and I feel good about it (arstechnica.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/905442

Comments

87
1
Staying engaged with AI plans: give inline feedback (huonw.github.io)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
88
1
Agentic Engineering (addyosmani.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
89
1
The kind of training that Actually Works for Learning Agentic AI (coding-is-like-cooking.info)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
90
1
Debugging with AI: Can It Replace an Experienced Developer? (www.developerway.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

TL;DR

So, what's the verdict? Can AI replace an experienced developer for debugging?

No, of course not. AI is very good at pattern recognition, and it can be very, very useful. It will do exceptionally well on standard stuff: schema validation mishaps, forgotten null checks, common runtime errors, you've seen it for yourself already. Personally, my debugging almost always starts with the LLM these days. With literally the prompts above: "here's what's happening, this is the log, fix it". Half the time, it manages to do that.

But even if the fix works, I always retrace it step by step and make sure it's the actual root cause. If the fix doesn't work, however, I almost never iterate with the LLM, other than asking it to find me something in the repo. As you've seen, half of its responses in this case will be very confident hallucinations.

91
1
My experience with vibe coding (haskellforall.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/900106

Comments

92
1
Programming Principles in the Age of AI: DRY (kirilltolmachev.dev)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/899285

Comments

93
2
AI Coding Assistants Secretly Copying All Code to China (www.schneier.com)
submitted 2 months ago by codeinabox@programming.dev to c/aicoding@programming.dev
0 comments fedilink
 
 

cross-posted from: https://lemmy.bestiver.se/post/899948

Comments