Shameless plug. But poor Indie hacker's log store based on similar concepts. Write logs to durable s3/r2 in parquet and querying with duckdb: https://github.com/amr8t/blobsearch
The big one that's missing as cost cutter. If you are a programmer, stay as close as you can to the code. Define the interfaces yourself and the core logic. You will know exactly what changes you want and know what tier of model to use.
Until Claude Sonnet 4, it was Meh no big deal. 4 onwards and Opus was when I was really surprised by the ability. But nowadays, I'm more convinced than ever that using AI for all code is a mistake. The sum total of productivity, although hard to predict, from anecdata seems to be a net negative if AI is blindly used everywhere. Using it at the periphery, observing, debugging etc is excellent aid. I use it at the day job I hate and at personal tasks that I don't have time for. But for personal projects I love, zero.
Coding was never the blocker and was a natural enforcer of quality. Healthy teams with strong opinions on quality will win eventually. I'm more hopeful after the bubble burst, companies will come back slowly to sanity.
Looks really slick!
I've been using Obsidian with git, and am thinking of moving back to the OG solution of simply using a text editor with a git repo. I'm wary of using cloud like google drive or dropbox for sync, especially if I'm using both phone and mobile to edit the same file throughout the day. I doubt using an external cloud really takes care of consistency and there's a possibility of losing data. Me being a developer can take the pain of a button click to git pull and resolve occasional conflicts.
To me this is fully solved solution for note taking with tools I already know and trust. Having said that, I'm gonna try Files.md for some inspiration on what I could be missing.
I've been having the same feeling too. At work, I try to do a hybrid prompt where I fill in things at method level with some placeholder pseudocode and let the prompt fill in the blanks. This helps with remembering and keeping a memory map. But its a lost cause keeping up with other's PRs that are often very verbose and high volume. For a lot of backend programming without a very complex domain, I think this works fine.
But I still want to be in touch with coding by hand and have ventured into systems programming, outside of work, which I feel AI is less useful for currently.
DuckDB is amazing. It has completely replaced my need of using Cloudwatch or Loki etc for logs. I simply emit parquet to s3 now and use DuckDB to query locally. No HA compute or paying cloud tax for log search.
just cancelled mine. Only reason to have it was I could get a lot more done with a single prompt. No reason why I shouldn't go to the model provider directly instead.
This is a huge concern and I fully agree with the post. Even though one might think I am not fully giving into AI, this was always the case etc. It still affects YOU and everyone else.
1. Software, often, isn't built in vacuum. Lots of companies are shoving AI down throats like it or not. Most Bigtech is heavily using metrics to get to 100% AI generated code. Reviewing is a nightmare.
2. New entrants (new grads etc) are largely AI first and are losing out on the safety and reliability aspects that are enforced automatically when you learn coding without AI.
IMO, teams need to agree on a set of principles on AI usage, concrete examples of where and how to use it. Perhaps its much more useful in parts of your system that's faster evolving and doesn't have too much core logic like testing frameworks etc
Simply discarding it as 'yet another tool' is part of the problem.
License makes a lot of sense. Many engineering fields have licenses. Needs to be made mandatory. Tech rapidly evolves which was an excuse. Well, a lot has stabilized now in terms of technologies.
Love Zed for my personal projects at home with Openrouter. But I cant use it at work as I'm forced to use claude code at work and find the VSCode+claude code combo better. I know zed has claudecode integration, but I found it to be very weak compared to zedagent+claudemodel. Has this improved?
This rings so true. Software Engineering should have stricter bar similar to med professionals. If we have leaked such lousy products and the public crowd thinks this is usable, it's a failure of the industry as a whole.
Do you need evidence that auto complete makes you productive? It's stochastically useful. That also means a certain percentage of it will lead to garbage that could easily negate all the benefits. The lower you go down the stack, the more trickier it gets. We as humans are so obsessed with AI right now it's unbelievable. Lots of attention could be spent at other areas of innovation instead of obsessing on LLMs
No expensive indexing or compute needed.