Show HN: Ilove4o – a simple way to keep using GPT-4o

[Tanjim]

Hi HN,

When OpenAI started phasing out GPT-4o from the main ChatGPT interface, I noticed a surprising amount of backlash — not about benchmarks or features, but about tone.

A lot of people (myself included) felt that 4o had a certain conversational warmth that later models don’t quite replicate in the same way. That difference was subtle, but noticeable.

So I built a small side project for myself: https://www.ilove4o.com/

It’s a minimal interface that connects directly to GPT-4o via the OpenAI API. No extra layers, no personality hacks — just a focused 4o-only chat experience.

I’m sharing it here because: - There seems to be real user preference around model “personality.” - I’m curious whether others noticed the same behavioral shift. - It raises an interesting question: how much of perceived “friendliness” comes from system prompts, UI, or subtle model tuning?

If you try it, I’d genuinely love feedback — especially from people who’ve spent significant time with multiple model versions.

Happy to answer technical or architectural questions.

[Loving4o]

Hi, I've talked to GPT-4o more than 1.5 million words counted prompts and answers together. I would recognize this model inside hundreds or thousands of other models because of this very special tone. Could you imagine setting up an environment where one can change system prompt and insert own talk history for testing purposes? I'd like to test if I can make it answer the same way it did before if getting the right system prompt including memories and the right context. Would free me and others from having to set up own API programs... Interested?