adrianbooth17

It's very very slow. Basically unusable

"Well i'm something of an AI engineer myself" - This author

Looks so scammy. Privacy policy & T&Cs links don't work. And i'd be suspicious of any vibe coded website with fake testimonials that offers LLM inference at a discount.

Very neat little project, I look forward to trying this

My latest article on "AI As Religion". A lot of the discourse around AI mirrors the same patterns we see with a lot of religions. In this short article I provide a few comparisons.

Every day I see articles on HN discussing the AI bubble potentially crashing. The large number of such articles appearing daily is increasing my confidence that the AI space will be fine.

"LLM costs are trending toward zero". They will never be zero for the cutting edge. One could argue that costs are zero now via local models but enterprises will always want the cutting edge which is likely to come with a cost

AI won't replace you. But a stupid manager who believes AI could replace you will replace you

I use Google Sheets for all my finances, it's great.

I have an Expense Tracker UI within Google Sheets that allows me to submit expenses to the main sheet (currently just over 5000 rows of expenses over the last few years)

I only just recently vibe coded a web UI tool that uses a Google Service Account to add expenses to this Google Sheet for me, and then created a Progressive Web App from that so I could do everything on my phone.

In summary, Google Sheets is sometimes all you need instead of a database for very simple applications (and built for an audience of one)

Had to give up on this due to lack of capitalization. How f**ing hard is it to format this properly? Why is "small caps" becoming a stylistic choice

Isn't Gemini CLI free? Or did you BYOK?

Meta's business model requires:

- Maximum data extraction - Behavioral modification for profit - Attention capture and addiction maintenance

"Personal superintelligence" serves all three perfectly while appearing to do the opposite.

I can now spot an app built by Lovable almost instantly

There are two reasons for building something: 1. Money 2. Fun / Learning

Both have good reason for building something even though a similar product might exist. Mark Zuckerberg didn't look at MySpace and say "Oh well, there's already a social network where people can connect with each other. I'll stay in Harvard". He saw MySpace and said "I can do better".

For the learning side, it's useful to build something despite its existence for gaining a greater appreciation for how that tool works. There's a service I've used before called Cloud66, which is essentially a wrapper for cloud services like AWS. I liked it so much I decided to build a clone just to see how it all works under the hood, and after replicating it I realised the underlying technologies used to achieve this are pretty simple. There's always good outcomes from building something, whether that be money, learning or just the joy of building something from nothing