161–170 of 603 posts
As in the former is hyped, but the latter - stopping to ask questions, reflect, what should we do - is really powerful. I find I'm more thoughtful, doing deeper research, and asking deeper questions than if I was just hacking something together on the weekend that I regretted later.
Earlier quoted context omitted.
> as a vibe coding skeptic, I was amazed. The interesting thing about all of this vibe coding skepticism, cynicism, and backlash is that many people have their expectations set extremely low. They’re convinced everything the tools produce will be junk or that the worst case examples people provide are representative of the average. Then they finally go out and use the tools and realize that they exceed their (extreme…
Im a vibe code skeptic because I dont consider it coding. I assume it can write some decent code, but that's not coding.
It's less that I'm a skeptic, but more that I'm finding I intensely abhor the world we're building for ourselves with these tools (which I admittedly use a lot).
Earlier quoted context omitted.
Fascinating since I found the recent Claude models untrustworthy for writing and editing SQL. E.g. it'd write conditions correctly, but not add parens around ANDs and ORs (which gemini pro then highlighted as a bug, correctly.)
If you aren't already (1) telling Claude Code which flavor of SQL you want (there are several major dialects and many more minor ones) and (2) giving it access to up-to-date documentation via MCP (e.g. https://github.com/arabold/docs-mcp-server ) so it has direct access to canonical docs for authoritative grounding and syntax references, you'll find that you get much better results by doing one or both of those thing…
As a recent example, I am working on a Rust app with integrated DuckDB, and asked it to implement a scoring algorithm query (after chatting with it to generate a Markdown file "RFC" describing how the algorithm works.) It started the implementation with an absolute minimal SQL query that pulled all metrics for a given time window.
I questioned this rather than accepting the change, and it said its plan was to implement the more complex aggregation logic in Rust because 1) it's easier to interpret Rust branching logic than SQL statements (true) and 2) because not all SQL dialects include EXP(), STDDEV(), VAR() support which would be necessary to compute the metrics.
The former point actually seems like quite a reasonable bias to me, personally I find it harder to review complex aggregations in SQL than mentally traversing the path of data through a bunch of branches. But if you are familiar with DuckDB you know that 1) it does support these features and 2) the OLAP efficiency of DuckDB makes it a better choice for doing these aggregations in a performant way than iterating through the results in Rust, so the initial generated output is suboptimal.
I informed it of DuckDB's support for these operations and pointed out the performance consideration and it gladly generated the (long and certainly harder to interpret) SQL query, so it is clearly quite capable, just needs some prodding to go in the right direction.
So far what I've noticed with Claude Code is not _productivity gains_ but _gains in my thoughtfulness_ As in the former is hyped, but the latter - stopping to ask questions, reflect, what should we do - is really powerful. I find I'm more thoughtful, doing deeper research, and asking deeper questions than if I was just hacking something together on the weekend that I regretted later.
I use this with legacy code too. “Lines n—n+10 smell wrong to me, but I don’t know why and I don’t know what to do to fix it.” Gemini has done well for me at guessing what my gut was upset about and coming up with the solution. And then it just presses all the buttons. Job done.
I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…
What exactly have you written with Claude Code? I have not tried it, for a variety of reasons, but my (quite limited, anecdotal, and gratis) experience with other such tools is, that I can get them to write something I could perhaps get as an answer on StackOverflow: Limited scope, limited length, address at most one significant issue; and perhaps that has to do with what they are trained on. But that once things get…
I think Claude Code is great, but I really grew accustomed to the "Cursor-tab tab tab" autocomplete style. A little perplexed why the Claude Code integration into VS Code doesn't add something like this? It would make it the perfect product to me. Surprised more people do not talk about this/it isn't a more commonly requested feature.
I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…
For me the sweet spot is for boilerplate (give me a blueprint of a class based on a description), translate a JSON for me into a class, or into some other format. Also "what's wrong with this code? How would a Staff Level Engineer white it?" those questions are also useful. I've found bugs before hitting debug by asking what's wrong with the code I just pounded on my keyboard by hand.
Over the holidays I built a plan for an app that would be worthwhile to my children, oldest son first. That plan developed to several thousand words of planning documents (MVP, technical stack, layout). That was just me lying in the sun with Claude on mobile. Today I (not a programmer, although programming for 20+ years, but mostly statistics) started building with Claude Code via Pro. Burned through my credits in ab…
Burning through your credits is normal. We're in the "lmao free money"/"corner the market" phase, where anthropic offers claude code at a loss. Recently they had to lower token allowances because they're haemorrhaging money. You can run "ccusage" in the background to keep tabs, so you're leas surprised, is all I can say. Enjoy the cheap inference while you can, unless someone cracks the efficiency puzzle the frontier…