Any tips for working with Gemini through its chat interface? I’ve worked with ChatGPT and Claude and I’ve generally found them pleasant to work with, but everytime I use Gemini the output is straight dookie
Even though I don't like the privacy implications, make sure you use the option to save and use past chats for context. After a few months of back and forth (hundreds of 'chat' sessions), the responses are much higher quality. It sometimes does 'callbacks' to things discussed in past chats, which are typically awkward non-sequiturs, but it does improve it overall.
When I play with it in 'temporary chat' mode that ignores past chats and personal context directives, the responses are the typical slop littered with emojis, worthless lists, and platitudes/sycophancy. It's as jarring as turning off your adblocker and seeing the garish ad trash everywhere.
You must be joking. I’ve turned that off after first month of use. It’s unbearable. “Oh since you are in {place i mentioned a week ago while planning trip but ultimately didnt go} the home assistant integration question changes completely”. Or ending every answer with “since you are salesforce consultant, would you like to learn more about iron smelting?”
I told Gemini I'm a software engineer and it explains absolutely everything in programming metaphors now. I think it's way undertrained with personalization.
Gemini has always felt like someone who was book smart to me. It knows a lot of things. But if you ask it do anything that is offscript it completely falls apart
I strongly suspect there's a major component of this type of experience being that people develop a way of talking to a particular LLM that's very efficient and works well for them with it, but is in many respects non-transferable to rival models. For instance, in my experience, OpenAI models are remarkably worse than Google models in basically any criterion I could imagine; however, I've spent most of my time using the Google ones and it's only during this time that the differences became apparent and, over time, much more pronounced. I would not be surprised at all to learn that people who chose to primarily use Anthropic or OpenAI models during that time had an exactly analogous experience that convinced them their model was the best.
I'd rather say it has a mind of its own; it does things its way. But I have not tested this model, so they might have improved its instruction following.
I too have felt these feelings (though I'm much younger than the author). I think as I've grown older I have to remind myself
1. I shouldn't be so tied to what other people think of me (craftsman, programmer, low level developer)
2. I shouldn't measure my satisfaction by comparing my work to others'. Quality still matters especially in shared systems, but my responsibility is to the standards I choose to hold, not to whether others meet them. Plus there are still community of people that still care about this (handmade network, openbsd devs, languages like Odin) that I can be part of it I want to
3. If my values are not being met either in my work or personal life I need to take ownership of that myself. The magic is still there, I just have to go looking for it
I’m always amazed and slightly envious of what programming languages with large developer bases can do. I mean if a language is Turing complete it can do anything, but JavaScript takes this to the extreme.
Mind you I never said anything about quality or performance, obviously doing everything in JavaScript comes with it’s own issues but if you were to say that someone got JavaScript running in the Linux kernel as a POC I wouldn’t even be surprised
Python pays the bills. If it was up to me I'd use a different language, but there is no denying that its got a strong story in just about every field now. As I've gotten older, I've come to realize that programming languages are vehicles for solving computer based problems, and I've learned to find joy in solving those problems in whatever language my company/project is using.
But in my personal projects, my favorite language to use it Dart.
My biggest Issue with Java, is that it isn't streamlined. There are multiple implementations of the jdk that could be used, Many different build systems, etc. The C# ecosystem is smaller for sure, but it is much more streamlined
I think it is quite high, especially for newcomers to the ecosystem. The popular sdkman CLI tool for managing JDK installations provides 17 different JDKs to install:
With the DotNet SDK for comparisons sake, there is but one provider, and package management is provided as first class citizen in the compiler CLI, removing the need to even pick a "gradle" or "maven" style build tool in the first place for almost any project.
It doesn’t negate the issue at all, especially as sdkman is an optional extra tool. If working with others, that default is not always going to be the one your team develops against either. If you are just trying to pick a jdk and don’t even know sdkman exists, a sensible person will rightly wonder why the ecosystem has fractured into 17 JDKs, or you won’t notice at all and blindly pick a download from the oracle website. I’ve seen it cause confusion many times for new (and old!) Java developers.
Checking a new developer has actually managed to install the correct JDK for a given project is still a thing I have to do, all the time.
Sdkmans docs also have no bearing on the multiple build systems in the java world too, which again simply a non-issue in DotNet and many others.
reply