stpedgwdgfhgdd

No worries. True, you need to learn new skills to work properly with Claude. However, 30 yrs of coding experience come in handy to quickly detect it is going in the wrong direction. Especially on an architectural level you need to guide it.

Embrace

I don’t think this an AI specific problem, same can happen with humans.

I build a code reviewer based on the claude code sdk that integrates with gitlab, pretty straightforward. The hard work is in the integration, not the review itself. That is taken care of with SDK.

Devs, even conservative ones, like it. I’ve built a lot of tooling in my life, but i never had the experience that devs reach out to me that fast because it is ‘broken’. (Expired token or a bug for huge MRs)

OR - OR? And - And

Exoskeleton AND autonomous agent, where the shift is moving to autonomous gradually.

Exactly, one out of four or three prompts require tuning, nudging or just stopping it. However it takes seniority to see where it goes astray. I suspect that lots of folks dont even notice that CC is off. It works, it passes the tests, so it is good.

Our product is so good, the users are willing to put up with a bug once and there.

We need to get marketshare by going fast!

It is frustrating how often things break in CC. Luckily issues are quickly fixed, but it worries me that the QA / automated testing is brittle. Hope they get out of this start-up mode and deliver Enterprise grade software.

That will make 300

https://killedbygoogle.com/

This thread is working pretty decently. No bots so far

I have 40 years of programming experience, started with assembler, nowadays mainly Go, K8s and the whole enterprise shebang. I’m a big fan and supporter of TDD and XP.

Claude Code will change your life when you learn how to program with it. However, if you are a programmer with not a lot of desire for automated tests and specs/designs, you are probably not going to be successful with it.

The art of coding has become a commodity. Validation and verification are the new art.

Internal Server Error

The comments are what makes the model understand your code much better.

See it as a human, the comments are there to speed up understanding of the code.

Indeed, the article links to the skill documentation which says:

Skills are modular capabilities that extend Claude’s functionality through organized folders containing instructions, scripts, and resources.

And

Extend Claude’s capabilities for your specific workflows

E.g. building your project is definitely a workflow.

It als makes sense to put as much as you can into a skill as this an optimized mechanism for claude code to retrieve relevant information based on the skill’s frontmatter.

The matching logic for a skill is pretty strict. I wonder whether mentioning ‘git’ in the front matter and using ‘gitlab’ would give a match for a skill to get triggered.

All for CLI tools, but they have their limits. Another party can update their mcp server and you get the new tools without a sweat.

E.g. with a Jira cli tool I have to write the skill and keep it up to date. With a MCP server I can delegate most of the work.

And why?

Climate change (no rain) but especially bad water mgt.

Headline should be:

The intervention by the Dutch government at the Nijmegen-based chipmaker Nexperia is being suspended.

Iteratively working is a MUST for more than trivial fixes. This continuous loop could work for trivial refactorings / maintenance tasks.

I’m letting Claude Code review the code as part of a gitlab CI job. It adds inline comments (using curl and the http API, nightmare to get right as glab does not support this)

CC can also read the inline comments and creates fixes. Now thinking of adding an extra CI job that will address the review comments in a separate MR.

Because Go has stronger compile-time type safety than Python. And of course concurrency.

Fwiiw I noticed that colleagues using other languages like Java and JS with Claude Code sometimes get compile errors. I never get compile errors (anymore) with Go. The language is ideal for LLMs. Cant tell how CC is doing lately for Python.

Vibe coding sucks at this moment in time. On the other hand, when was the last time you looked at assembler code and thought, mmmm, I do not like the style? There is also room for optimization. If i would have written this myself, it would be way faster.

l'histoire se répète

Try Anthropic’s Claude Agent SDK and let Claude orchestrate the subagents, the websearch and a sandbox to do some statistics.

A computer is all you need.

I sometimes have to decide between running Claude Code headless with a prompt or let CC generate an application based on the prompt. (coining: Codification Threshold tradeoff)

The tradeoff is that the prompt is non-deterministic, but also more flexible. It can handle unknown situations. The generated code executes much faster and reliable for known situations.

If auto-learn would reduce the non-deterministic nature, i.e. chance of failing, that would speed up software development.

The person in the Cursor platform is raising a different question and a valid one. We have tons of these frameworks out there, openspec, amplifier, etc. The ultimate dream is to have these subagents work in the background autonomously.

However reality tells us that you constantly have to keep Claude on the right track. Nudge here, nudge there. Close code reviews. Test, test more. Very interactive. Superpowers to the engineer.

It is this contradiction that also makes me believe that it will take another year for agents to work on enterprise codebases autonomously. Maybe more, look at autonomous self driving, surprisingly hard to get to the last 10%.

I prefer:

Agentic coding, inner loop, the stuff an engineer does on his laptop. Agentic engineering, outer loop, sdlc across the organization

Not perfect, but good enough.

+1

It is just a new way of coding. And indeed what the blog post said, if you are experienced, you will benefit the most as the AI agent will make similar mistakes as a junior and you will be able to recognize them.

But indeed, the fun part of coding a couple of routines is gone. That is history.

+1

ChatGPT’s generic search will not be that good compared to apps specialized in this.

I tried buying a special kind of lamp this weekend, all LLMs and google sucked at this. The conversation did not help in finding more fine grained results.

True, you need to instruct the AI agents to include this.

In our case the agent has access to Jira and has wider knowledge. For commit messages i don’t bother that much anymore (i realise typing this), but for the MRs I do. Here i have to instruct it to remove implementation details.