- cross-posted to:
- technology@lemmy.world
- technology@beehaw.org
- cross-posted to:
- technology@lemmy.world
- technology@beehaw.org
The language this guy is wielding is cringe as hell, has LinkedIn energy all over it.
Interesting, but for some reason I found it very hard to read and get anything of substance out of the whole thing. Anyone care to help a dumb dumb out? Or is it just as fluffy as it seems?
Also, is the newsletter any good? Or is it mostly speculative non-fiction with words thrown around that don’t really amount to anything?
Don’t mistake my sarcasm for disinterest. I’m genuinely curious.
I don’t know anything about the newsletter. The core of the article seems to be observing a shift in AI/ML/LLM opportunities. Where before, most people in the field were developing the base models and doing the arduous and highly complex work of training models (what the author calls ML Engineers), now the majority of this field will be people who use those pre-made and pre-trained models, tweaking and applying them for more and more specific and quantifiable uses (what the author calls AI Engineers). He drew a malleable line between the two as whether you’re interacting with the model directly or via an API.
Thanks for summing it up! I get the point of the article a bit more clearly now.
I wonder if “AI engineer” isn’t kind of superfluous in that case? It’s essentially just the new normal for software developers/engineers. Another API or tool to interact with to produce whatever product we’re building. Where does the specialist competencies come in, besides having a more intimate knowledge of the APIs and basic understand of how this tech works?
I agree with how you characterized it and the term “ai engineer” didn’t resonate with me as defined by the author. If such an engineer doesn’t need to know about the data involved (“nor do they know the difference between a Data Lake or Data Warehouse”) then I don’t think they will be able to ship an AI/ML product based on data.
New titles can be helpful for sorting out different roles with some shared skillsets such as the distinction which emerged between Data Scientist and ML Engineer at some companies to focus the latter on shipping production software using ML.
I had the bing bot give a summary this super long article,
Sure, I can help you with that. Here is a summary of the article:
The article is about the emergence of a new role in software engineering: the AI Engineer. The author argues that AI Engineers are different from traditional Machine Learning or Data Engineers, because they use APIs and pre-trained models to build AI products, rather than training their own models from scratch. The author claims that AI Engineers can leverage the power of Foundation Models, such as large language models (LLMs), to solve a wide range of AI tasks that used to require years of research and a dedicated team. The author also predicts that AI Engineers will be the highest-demand engineering job of the decade, and announces a new conference and network for AI Engineers. The author provides examples of AI Engineers from various companies and domains, and contrasts them with other types of engineers and researchers. The author also discusses some of the trends and challenges that AI Engineers face, such as GPU hoarding, generative AI, code generation, and Python vs JavaScript. The article ends with a call to action for aspiring AI Engineers to join the community and make this a thing.
I feel like this is just describing the future of business processing consultants. Like there’s already a role for this, unless I’m missing something?