I have not fired a technical writer, but writing documentation that understands and maintains users focus is hard even with llm. I am trying to write documentation for my start up and it is harder than I expected even with llm.

Kudos to all technical writer who made my job as software engineer easier.

I feel local rag system , slows down my computer (I got M1 Pro 32 GB)

So I use hosted one to prevent this. My business use vector db, so created a new db to vectorize and host my knowledge base. 1. All my knowledge base is markdown files. So I split that by header tags. 2. The split is hashed and hash value is stored in SQLite 3. The hashed version is vectorized and pushed to cloud db. 4. When ever I make changes , I run a script which splits and checks hash, if it is changed the. I upsert the document. If not I don’t do anything. This helps me keep the store up to date

For search I have a cli query which searches and fetches from vector store.

This isn't easy to prove, but the sentiment in our field for a very long time is that the interviews are frequently the hardest part of the job.

That makes sense. Safari is so smooth now in iOS. Moved from Firefox.

Working on Ai agent (not chatbot) for customer support with automatic human handoff to Slack( in future for Zendesk, Teams, Jira)

Focusing on creating a omnichannel ai-powered support platform on Slack.

And you forgot the js library that lets you check if the number is odd https://www.npmjs.com/package/is-odd

Funny enough there is another library which checks if it is even https://www.npmjs.com/package/is-even

Both written by the same (somewhat notorious) purveyor of trivial shenanigans disguised as resume bullet points.

I feel it is hyped product oversold to people who cannot told. When we developers tell them that it cannot do as much as you expect, they think that we are afraid of loosing our job and downplaying the AI.

Like everyone said, my productivity boost is in 1-4% range and not more than that.

I actually have flashbacks from the crypto hype, with people coming up with exactly the same arguments: that we don't understand blockchain, that we don't get how web3 is revolutionary, that we don't grasp the consequences of the revolution and so on.

The difference here is that LLMs do have some genuine use cases, it's just they are far away from the hype.

I writing this just after the night end llm cannot even replace to using Trans i18n react component if it is not in context of the file. We are still far from agi