whats wrong with langchain ?

I haven't used it in a year, but my experience was it frequently broke in all sorts of ways. I have since avoided it like the plague.

I hear you. Had the same experience. It's matured a lot since then though. Got back to it a few weeks ago and it feels surprisingly stable.

Does it still have the "abstraction hell" issue when trying to work with it for custom, non out-of-the-box use cases?

it's much more stable now.

Does it still put you in dependency hell though, where you can't add new packages without causing tons of version conflicts?

Howdy! Erick from LangChain here. If anyone is seeing version conflicts on particular packages, please let me know!

These usually stem from overly strict constraints in the underlying sdks for the integrations, and in general we've been pretty successful asking for those constraints to be loosened. The main "problem" constraint we've seen in the past has been on httpx. Curious if you've seen others!

Can you elaborate on this? Do you automate replying to emails? Coding? Or just general productivity?

Also, the data doesn't seem to show that people who follow trends end up making more. It's quite the opposite - focusing on niche languages like Go, Rust or frameworks like Flutter can make you more.

You have to advance your career. Just being employed will not get you more money.

Okay, sounds solid but dummy question: What are my chances of doing this if I'm from Europe? Also, I don't have a full UNI degree, I dropped out after I got my Bachelors.

Fortunately big tech jobs are available in EU too. Highest salaries might trickier without moving to US, shouldn't be too hard to transfer to US once you get a job at one if you want to. Making quite a high salary without moving is possible too (though still need to be a in a major metro that has big tech companies.)

Getting a US visa without a degree will be extremely difficult, and so migrating may not be an option for you.

Do researchers make any real money? I feel like all around I hear about it being stale there as far as funding goes.

Researchers are in a unique position to get paid to discover things. Its a lottery in that what they publish could potentially be worth tremendous money in industry, but its a safe gamble because if everything else goes wrong they are still employable with a higher than average salary doing work that is less boring than average.

Thanks a lot for the advice.

Yea I can hear what you wrote about Germany. I currently work with a client who outsources some of their management work to Germany and apart for the titles people have before their names, their technical knowledge is really poor.

As far as the startup route, I'm experimenting with various things on the side but do not rely on them. I suppose it might be worth trying to build some "pluggable" integrations into processes of non-tech companies and charge monthly for the service. I don't wanna call it a SaaS yet, but well see.

I also know a guy that's more on the dev side but he makes really good money being an expert in various banking systems. Rarely works overtime and is fully remote. That sounds like a pretty good strategy as well.

id like to emphasize i didnt say anything about the skill levels of german engineers. ive worked with really talented ones, and poor ones. but for me its impossible to land a job there, having no education and certs. definitely feel u. a lot of people u meet in corporate arent the hackers you expect. like anywhere, most people do the minimum not to get fired. and some people do all the work and suffer burnouts :D. wonderful world!

Not sure if there what the term for this is, but rather than looking at the probability of X happening we should rather look at the "inevitability" of X happening in the context of the environment.

In my experience, even though nature looks chaotic there is a very strict order to things which has evolved over millions of years and is a result of looking for the "most optimal way" to achieve a goal. A good example might be mycelium optimizing routes to nearby resources. Another might be ant colonies creating tunnels that are effective to navigate.

The problem is, in my opinion, that we do not know what the final goal is. Therefore we cannot begin to analyze the inevitability of something as us, or life in general, happening. The answer may be perhaps found in religion or some similar "greater than life" endeavor.