Skip to main content

How my work has changed in the past few years

When I started at my current job 3ish years ago, we had nothing but a few PowerPoint slides and a Figma prototype.

I recall talking with one of the founders, whom I had worked with some 10 years ago, and pointing out that the very next step after PowerPoint and Figma was still the same as it had always been: translating those slides and mockups into CRUDs, forms, and other basic building blocks.

Sure, all the new fancy tools and frameworks (we had jQuery then) help, but I still had to tinker with very basic primitives like tables and forms. I could not just say, "here is a table, here is a form." Well, yes, technically I could, but I still needed to write a lot of code to make a working form or table.

This was around the time of GPT-3, Copilot beta, and very early Cursor. I did attempt to use them, but they could only perform very basic tasks and were pretty much useless for frontend work.

We, being one of the first-wave "ChatGPT wrapper" startups has naturally pushed me toward being a heavy LLM user, both in how I do my daily work and in the kinds of features I build.

Here are some reflections on how my work has evolved from our humble starting point.

LLM-assisted development was a thing in 2023. Back in those Copilot autocomplete days, I remember thinking this is absolutely wonderful. I have a domain object shape in my head, and I can just start typing, and it will autocomplete the properties and methods. In the first decade of my career, IDEs improved to some extent, reducing the amount of menial typing, but you still had to do a lot of it.

If the LLM progress had stopped at that level, it would still have been a huge improvement and would have made my work more satisfying. I like thinking about domain objects and their relationships; writing them is just a chore.

But of course, the progress did not stop there.

Now I can just describe the domain and the problem I want to solve, and the LLM will give me a solution. Everyone knows there are caveats to this, but more and more, it just works.

So, recalling that past discussion with the founders, I no longer have to spend my days typing CRUDs, forms, tables, and back-office tools. The work is still being done, but in a very unexpected way. I can now summon ghosts to build me a table that works.

That raises the question of what to do with the time freed up elsewhere.

Of course, I can do more things. I can try out different ideas more quickly and push them out.

That also means I need to have good ideas. I do have ideas. I always find something to do, something to improve, and something to build.

Does that mean the product will be better? Maybe. I like to think I have decent product taste: not great, but enough to get a "Looks good to me" from users.

It could also be that I don't have good product taste. I can push out more things faster, and the result might simply be a product with a ton of features. Everyone likes a product with a lot of features, right?


What has become painfully obvious is that the technology is the easy part for typical SaaS products. If your edge is being fast at turning Jira tickets into working software, that edge is eroding quickly. 

A new moat you can start digging is to improve your product taste. Also, it would not hurt to be able to talk to customers effectively, which is way harder than asking, "What do you want me to build?"

Unlike hard technical skills, like weeding out N+1 queries, these skills don't have clear or well-defined solutions, making them painful to learn for a programmer's brain.

Labels:

Comments

Post a Comment

Popular posts from this blog

I'm not a passionate developer

A family friend of mine is an airlane pilot. A dream job for most, right? As a child, I certainly thought so. Now that I can have grown-up talks with him, I have discovered a more accurate description of his profession. He says that the truth about the job is that it is boring. To me, that is not that surprising. Airplanes are cool and all, but when you are in the middle of the Atlantic sitting next to the colleague you have been talking to past five years, how stimulating can that be? When he says the job is boring, it is not a bad kind of boring. It is a very specific boring. The "boring" you would want as a passenger. Uneventful.  Yet, he loves his job. According to him, an experienced pilot is most pleased when each and every tiny thing in the flight plan - goes according to plan. Passengers in the cabin of an expert pilot sit in the comfort of not even noticing who is flying. As someone employed in a field where being boring is not exactly in high demand, this sounds pro...
Post a Comment
Read more

RocksDB data recovery

I recently needed to do some maintenance on a RocksDB key-value store. The task was simple enough, just delete some keys as the db served as a cache and did not contain any permanent data. I used the RocksDB cli administration tool ldb to erase the keys. After running a key scan with it, I got this error Failed: Corruption: Snappy not supported or corrupted Snappy compressed block contents So a damaged database. Fortunately, there's a tool to fix it, and after running it, I had access to the db via the admin tool. All the data was lost though. Adding and removing keys worked fine but all the old keys were gone. It turned out that the corrupted data was all the data there was. The recovery tool made a backup folder, and I recovered the data by taking the files from the backup folder and manually changing the CURRENT file to point to the old MANIFEST file which is apparently how RocksDB knows which sst (table) files to use. I could not access the data with the admin tool, ...
Post a Comment
Read more

PydanticAI + evals + LiteLLM pipeline

I gave a tech talk at a Python meetup titled "Overengineering an LLM pipeline". It's based on my experiences of building production-grade stuff with LLMs I'm not sure how overengineered it actually turned out. Experimental would be a better term as it is using PydanticAI graphs library, which is in its very early stages as of writing this, although arguably already better than some of the pipeline libraries. Anyway, here is a link to it. It is a CLI poker app where you play one hand against an LLM. The LLM (theoretically) gets better with a self-correcting mechanism based on the evaluation score from another LLM. It uses the annotated past games as an additional context to potentially improve its decision-making. https://github.com/juho-y/archipylago-poker
Post a Comment
Read more