Ruby Koans and Puzzle Design diegobit, 11 Aug 2025

DHH talks about Ruby like a language you write poems in, beautifully designed for ergonomics. He recalls the epiphany he had when first encountering its metaprogramming... so I finally decided to try it ...

--More--

Crawling shouldn't be that hard diegobit, 24 Apr 2025

o3 has a powerful search – it can even keep searching the web for minutes until it finds the precise location where a picture was shot. Maybe my Opinion Search is already outdated...

Sometimes all I want is to download the documentation of a website and upload it to Claude or ChatGPT project documents. When I'm about to work on something for a few days where I know the required knowledge is newer than the LLMs' cutoff, I don't want to ask the llm to do a web search at the start of every chat to re-load all the context ...

--More--

An MCP server for my Aranet4 CO2 sensor diegobit, 20 Apr 2025

I recently bought an Aranet4 CO2 sensor to monitor the CO2 concentration in my home. There are studies showing that high CO2 concentration decreases cognitive performance significantly (I recommend to start your research with this video from DHH).

The Aranet4 seems to be (one of) the only devices with a dedicated co2 sensors, and is for sure the gold standard. Unfortunately, even though it is quite expensive (I spent 220 euros in italy), you cannot store historical data on the mobile app, which is limited to the 7 days stored in the device itself.

That's why I built these ...

--More--

Thoughts on ARC-AGI-2 diegobit, 03 Apr 2025

The recent ARC-AGI-2 release makes me think about how we learn and puzzle videogames. Recently OpenAI recent o3 models reached 75.7% and 87.5% accuracy on the first version of the ARC-AGI benchmark. Hovewer, it had a per-task cost of 200$ for the high efficiency version, and much more for the low efficiency version. They don't mention the cost, they just say it requires 172x the compute. You can make an estimate yourself... I won't make an analysis of o3 and LLMs, for those I'll refer to the blog post and the YouTube interview with Machine Learning Street Talk. What matters ...

--More--

How I replaced all my searches with LLMs diegobit, 19 Mar 2025

Google search is full of sponsored content, ads, listicles, increasingly more stuff is made by garbage AI. What should we do? I stopped hoping for a redemption, or for other real search engines to replace it — I'm stubbornly still tring to use DuckDuckGo, but each alternative has some flaw that make it worse than Google in the end. I've been using ChatGPT with its search feature for a while now, and I'm convinced LLMs are the best way to search in 2025. No ads, personalized answers, no spam... Some day I'll make my own "deep research like" agent with ...

--More--