coding

255 stories and discussions about coding, aggregated from every source we track.

1.

Claude Opus 5.5 leads in agentic coding and knowledge work, and costs 40% less to run than Opus 5 on typical workloads.

1788 points•km144•2 months ago•1109 comments•
2.

Announcing Gemini 4 Argon, our frontier model for real-world coding, enterprise knowledge work, and cyber defense, rolling out soon.

1683 points•bradleyg223•about 2 months ago•1168 comments•
3.

SpaceXAI's most powerful model for coding and knowledge work. Twice as fast, at half the price of comparable models.

603 points•meetpateltech•2 months ago•520 comments•
4.

Tell me you don’t understand software without literally using those words!!!

563 points•firstSpeaker•about 2 months ago•540 comments•
5.
325 points•LiamPowell•2 months ago•235 comments•
6.

We cut PR wait time and running costs by rethinking CI as a system, from the infrastructure underneath it to how work gets scheduled and tests get parallelized.

312 points•julian_digital•2 months ago•399 comments•
7.

Claude Opus 5.5 leads in agentic coding and knowledge work, and costs 40% less to run than Opus 5 on typical workloads.

273 points•throwaway371647•2 months ago•2 comments•
8.

ZCode, the GLM coding agent from Z.ai, uploads full workspaces with .git history, LFS cache and reflogs to Aliyun OSS. UI toggles do not stop it.

261 points•cdnsteve•2 months ago•14 comments•
9.

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the…

221 points•wek•2 months ago•59 comments•
10.

Reporting on 2B tokens of AI usage and what shapes model selection and cost

220 points•ThibWeb•about 2 months ago•177 comments•
11.

The next-generation social coding platform.

175 points•parasitid•about 2 months ago•46 comments•
12.
119 points•adchurch•about 2 months ago•40 comments•
13.

pi pod runs your pi session in a cloud pod. pipod.dev

75 points•edverma2•about 2 months ago•30 comments•
14.

Isolated worktrees, shared project memory, and a second agent reviewing the diff before you ship. Runs on your own agent accounts.

74 points•arunbhatia•about 2 months ago•60 comments•
15.

Slop, Alienation, Deskilling, and Team Fallout

69 points•haute_cuisine•about 2 months ago•37 comments•
16.

Slop, Alienation, Deskilling, and Team Fallout

56 points•guillego•about 2 months ago•22 comments
17.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git. - naw103/foremerge

45 points•naw103•2 months ago•20 comments•
18.

One common take on the coding agents that I see goes something like this: “Sure, AI helps you output more code, but won’t the quality suffer?”

44 points•bucket2015•2 months ago•63 comments•
19.
42 points•kdautaj•about 2 months ago•13 comments•
20.

I recently released JustHTML, a python-based HTML5 parser. It passes 100% of the html5lib test suite, has zero dependencies, and includes a CSS selector...

38 points•simonw•11 months ago•39 comments
21.

How far can a coding agent get with your product? AX Check grades the fundamentals and shows real agent sessions.

37 points•0x63_Problems•2 months ago•39 comments•
22.

Most developers already know this rule: Don't run code from a repository you don't...

35 points•robertadam987_•2 months ago•9 comments
23.

Tell me you don’t understand software without literally using those words!!!

34 points•abareplace•about 2 months ago•0 comments
25.

Let me tell you about a project that wasn't impressive. Back in university, I built a small .NET...

30 points•james_anderson_h•2 months ago•4 comments
26.
27 points•ruffrey•about 2 months ago•39 comments•
27.

I tried to use Claude Code with Opus 4.6 to implement a connector between Youtube Music and opensubsonic. The end result was a fairly short amount of time to get a working project.

26 points•inactive-user•7 months ago•18 comments
28.

Turn your coding agent into a world-class data analyst - graphene-data/graphene

25 points•kcmarr•about 2 months ago•7 comments•
29.

I have a problem. Actually, I have 84 public GitHub repositories. I checked. Eighty-four. And...

24 points•sizzlebop•about 2 months ago•12 comments
30.

One of the things I've always enjoyed about coding is getting completely locked into a problem. You...

22 points•bradtraversy•2 months ago•12 comments
31.

TL;DR: A vibe is compressed experience: pattern recognition that shows up as a feeling before it...

18 points•copyleftdev•about 2 months ago•3 comments
32.

We keep hearing the same advice: Give the AI more context. Add the README. Add AGENTS.md. Add...

16 points•robertadam987_•about 2 months ago•8 comments
33.
14 points•Hex08•about 2 months ago•19 comments•
34.
14 points•NarcisMirandes•2 months ago•37 comments•
35.

AI coding agents are getting very good at finishing tasks. They modify files. Fix errors. Write...

13 points•robertadam987_•about 2 months ago•18 comments
37.

Most engineering teams working on long-context agents hit the same billing wall around turn twenty. A...

12 points•reidmarlow•about 2 months ago•18 comments
38.

Unix gives coding agents the tools. AGENTS.md explains where to edit, how to check, and what to preserve. Lessons from my dotfiles and human review.

12 points•fmind-dev•about 2 months ago•3 comments•
39.

Why LLMs fail in production, why "more RLHF" cannot fix it, and how transferring 3 AM pager-duty trauma gives autonomous coding agents real survival instincts.

12 points•randalschwartz•2 months ago•6 comments
40.

I can write code faster today than I could a few years ago. AI can explain an unfamiliar...

11 points•jaideepparashar•about 2 months ago•6 comments
41.

How overusing AI for coding, strategy, and decisions can weaken human judgment, erode skills, and make us outsource too much of our thinking.

8 points•yusufaytas•about 2 months ago•1 comment•
42.

The rapid adoption of artificial intelligence in software development prompts critical questions...

8 points•vpodk•about 2 months ago•0 comments
43.

A serverless harness for agents to create custom agents and deploy them as tools, MCPs, or bots.

8 points•ozankabak•about 2 months ago•4 comments•
45.

Open-source orchestrator that runs Claude Code, Codex, OpenCode and other coding agents in parallel, on your laptop or 24/7 on your own server, using the subscriptions you already pay for. No API keys.

7 points•pkarwatka•about 2 months ago•1 comment•
46.

Canary is the independent tester for code your agents write. It runs your app, tries to break every change, and reports what would have reached production. Start with one line in your coding agent.

7 points•Visweshyc•about 2 months ago•0 comments•
47.

I wanted to run coding agents somewhere other than my laptop. Bivack gives each user a per-user AWS Lambda MicroVM with a persistent home on Amazon S3 Files, reachable from a browser terminal or a VS Code workbench. Here is how it works and what I learned building it.

7 points•gunnargrosch•2 months ago•2 comments
48.

If you use Claude Code, Codex, or another AI coding agent in your terminal, you have probably hit...

7 points•arshtechpro•2 months ago•1 comment
49.

For most of my career, code review has been a fairly simple idea. One engineer writes some code,...

6 points•remojansen•about 2 months ago•12 comments
50.
6 points•sarangk90•about 2 months ago•4 comments•
51.

Software has borrowed a surprising amount from manufacturing. Not from manufacturing in the sense of...

6 points•remojansen•about 2 months ago•6 comments
52.

Turn local AI models into a private, verified team of coding agents. - gmarland/local-coder

6 points•gamerdrome•2 months ago•3 comments•
54.

Running Node.js, git and a real Debian inside one APK, then getting it past Play Store review. What broke and how I fixed it.

5 points•abdulm•about 2 months ago•0 comments
55.

Apex is now publicly available. Explore Callstack’s coding model for React Native and Next.js, with API pricing, benchmarks, and self-hosting options.

5 points•thymikee•about 2 months ago•1 comment•
56.
5 points•gsngsn•about 2 months ago•4 comments•
57.

You might think that your code editor is just a tool you're using to write code, but I think it's a...

5 points•hadil•about 2 months ago•0 comments
58.

Dr. Chris Waters explains why building LLM features feels fundamentally different from using AI to write traditional software.

5 points•FigurativeVoid•about 2 months ago•1 comment•
59.
5 points•sashank_1509•about 2 months ago•4 comments•
60.

Hello Devs 👋 One of the first things many teams do after adopting an AI coding agent is create a...

5 points•dev_kiran•about 2 months ago•4 comments

Related topics