When I search this topic online, I always find either wrong information or advertising lies. So what is actually something that LLMs can do very well, as in being actually useful and not just outputing a nonsensical word salad that sounds coherent.
Results
So basically from what I’ve read, most people use it for natural language processing problems.
Example: turn this infodump into a bullet point list, or turn this bullet point list into a coherent text, help me with rephrasing this text, word association, etc.
Other people use it for simple questions that it can answer with a database of verified sources.
Also, a few people use it as struggle duck, basically helping alleviate writers block.
Thanks guys.
Just rewrote my corporate IT policies. I feed it all the old policies and a huge essay of criteria, styles, business goals etc. then created a bunch of new policies. I have chatgpt interview me about the new policies, I don’t trust what it outputs until I review it in detail and I ask it things like
What do other similar themed policies have that I don’t? How is the policy going to be hard to enforce? What are my obligations annually, quarterly and so on?
What forms should I have in place to capture information ( i.e. consultant onboarding).
I can do it all myself but it would be slower and more likely to have consistency and grammatical errors.
I use it for helping me learn German but only for explaining things like grammatical rules, concepts, or word uses.
Do not ask it to translate or write something for you. It will make lots of grammatical mistakes. I find that it often misgenders or uses the wrong case for nouns in a sentence.
I was surprised how effective it was for getting a checklist of things I should do to get a car that hasn’t been running for 30 years back on the road and asking for instructions for each step and things I should keep in mind
Outside of that it’s become a Google replacement for software development questions
You do kinda have to know about the things you ask it about so you can spot when it’s bullshiting you
I use it for coding templates. Like build a basic mvc crud then I’ll fill in the blanks.
None of the models are very good at the whole picture, but they save me time. I’ve tried to do more but it just lies about libraries that dont exist.
It’s really good in statistics, but you need to know enough statistics to know what to ask. Just today I needed to write a PyStan script for doing some MCMC and it’s helped me to write it, structure the data and understand the results of the experiment. Then, it confirmed my suspension that the chosen model was not very good for my data and tomorrow I’m trying with another probability distribution.
I use it to help me come up with better wording for things. A few examples:
-
Writing annual goals for my team. I had an outline of what I wanted my goals to be, but wanted to get well written detail about what it looks like to meet or exceed expectations on each goal and to create some variations based on a couple of different job types.
-
Brainstorming interview questions. I can use the job description and other information to come up with a starting list of questions and then challenge the LLM to describe how the question is useful. I rarely use the results as-is, but it helps me to think through my interview plan better than just using a list of generic questions.
-
Converting a stream of thought bullet list into a well written communication.
-
Writing emails, brainstorming
I think using LLMs with RAG (aka tools) is more useful and reliable than relying only on training data that the model does its best to represent.
For example, using a search engine to find results for a query, downloading the first 10 results as text, and then having the LLM answer subsequent queries about those sources, or another example would be uploading a document and having the LLM answer queries about its contents.
This is also advantageous because much smaller and quicker models can be used while still producing accurate results (often with citations to the source).
This can even be self hosted with Open WebUI/ollama.
Website building
Would you mind expanding on this? How do you use the LLM to aid in building websites?
Copying some HTML and CSS code into the llm and saying “change it to make it do xxxxxxx”
Database queries, especially OpenSearch/ElasticSearch
When I’m in a hurry I use them for
- longer more complex excel formulas.
- to create powercell scrips to manipulate large csv-files.
I used it to teach me app script and it was 90 percent accurate
Philosophy.
Ask it to act as Socrates, pick a topic and it will help you with introspection.
This is good for examining your biases.
e.g. I want to examine the role of government employees.
e.g. when is it ok to give up on an idea?I ask it increasingly absurd riddles and laugh when it hallucinates and tells me something even more absurd.
Not exactly sure this is the “right way” to use them, but I use one as an autocomplete helper in my IDE. I don’t ask it to code anything, just use it as autocomplete.
Majority of the time, it works well, especially in common languages like Python.
It has helped with some simple javascript bookmarklets
Also, translation and summarisation. Though, I do double check.
