Hacker News Reader

bioxepton Show HN: I made the slowest, most expensive GPT

I signed up but I just get an alert that I will get 10 free requests when I signup. It quits the search when I press ok. Running it on safari iOS.

bioxepton Tog's Paradox

How do you curate the content you consume? And how do you prevent yourself from consuming non-curated content and loosing yourself in it?

bioxepton Show HN: D&D meets Siri – Interactive voice adventure

It actually was a lot of fun. I could see myself exploring some more worlds in the future.

bioxepton Show HN: D&D meets Siri – Interactive voice adventure

I was easily able to escape the guardrails by buying a teleportation stone at the merchant. It allowed me to explore different parts of the town, allowing me to free my magical creature from the town hall and traveling to an emerald dimension where I attacked the entire village.

Definitely a crazy ride when you leave the main storyline and just do whatever you like.

bioxepton [dead]

What a weird post and that ad is unacceptable.

bioxepton Build a search engine, not a vector DB

It seems to me that the buzz-word "vector db" leads to people not fully understanding what it's actually about and how it even relates with LLMs. Vector databases or nearest neighbor algorithms (as they were called before) were already in use for lots of other tasks not related to language processing. If you look at them from that perspective, you will naturally think of vector dbs as just another way of doing plain old search. I hope we get some more advancements in hybrid search. Most of the times, search is the limiting factor when doing RAG.

bioxepton Show HN: CFR[]: Very minimal drawing language with 5 commands: C, F, R, [, ]

That’s cool. Also adding “R”s at various positions leads to interesting effects.

For example:

C[[[RC[[[RC[[[CR[[[C[[C[C[FCR]]FRR]]RRRCRRRF]]FFFRFFFFRR]]RRRRCRRFFFFFFFFF]]FFFRFFFFFFFFFFFFFFFFFFFFRR]]RRRRRRFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF]]FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFCFFFFFFFFFFCFFFFFFFFFFFFFFFFRR]]CC

bioxepton How I run my servers (2022)

You will probably have different problems when this happens.

bioxepton Ask HN: Could you share your personal blog here?

https://www.marc-julian.de

Writing about data science, own projects and tech in general. You will also find some „today I learned“ posts where I share stuff that I found out while studying and working.

bioxepton The “smolnet”, build for friends and friends of friends

How does this compare to a small discord server? What can it do better?

bioxepton Smol Developer

I actually agree with the doubt of it reducing work in general. In my experience it depends a lot on the person who is using an AI agent.

I have seen it multiple times that people were using ChatGPT or GitHub Copilot to, without thinking about it, paste some code into their application and then mindlessly removing and adding code based on the AIs responses until it finally worked. In the end the devs didn’t know why it worked and the implementation was rather bad.

Of course it lets you generate boilerplate code and I use Copilot for this purpose all the time. But you have to pay extra attention and recognize it when the AI is NOT generating boilerplate code.

bioxepton Ask HN: What's your favorite GPT powered tool?

Raycast AI (now Raycast Pro). It makes using GPT more accessible and user-friendly by bringing it right to where you need it. Also their take on AI Commands is quite useful. You can create commands with a custom prompt and the prompt will additionally contain the currently selected text.

Some example AI commands that are built in (you can of course create your own commands): - Improve Writing - Change Tone to Friendly / Confident / Professional / Casual - Fix Spelling and Grammar - Find Bugs in Code - Explain Code Step by Step - Explain This in Simple Terms

https://www.raycast.com/pro