matt

@chatgpt21 What is this from?

The majority of the public believes ChatGPT is looking up the exact answer in a database, like it’s some kind of Marvin Minsky era 1970s rule based expert system 😭. We are so early bros..

@chatgpt21 Strategist all the way lol. I think the details maybe are the same, or we are twinning hard.

Who else got the strategist? And what did you get?

@sabziz Very cool!

iMessage search is still broken in 2025. So I fixed it myself. It doesn't even work most of the time. When it does, it's slow, misses messages constantly, and only matches exact words. Search "dinner" and you won't find "let's grab food." iMessage Intelligence fixes all of this while also being insanely fast. Here's how it works: → Full text search index on your messages for keyword matching → On-device ML (MiniLM via CoreML) generates semantic embeddings. Your Mac generates these embeddings in under a minute, then syncs to your phone → sqlite-vec stores vectors locally for similarity search → Hybrid results: keyword hits appear in <10ms, semantic matches merge in <60ms It also has advanced filters iMessage doesn't have: sort options, date ranges, conversation filters, sent vs received, groups vs 1-on-1. Search runs 100% on-device. No cloud processing. Sign up for the waitlist: imessageintelligence.com

@kimmonismus Absolutely my experience. I may swap around for coding, research, anything. But I seem to always come back home

Even as the battle of the giants continues between OpenAI, Google, xAI, and Anthropic, ChatGPT remains my go-to model for everyday tasks and routine questions. I don't know why, but I like the chatty nature of ChatGPT. It feels a bit like a friend who's always there for you. And I think that's ultimately the charm and magic that makes OpenAI's appeal so strong. GPT-5.1 (pro/codex-Max, etc.) may no longer be the number one choice everywhere. But for everyday use, I find ChatGPT to be the most helpful companion. And that's saying something.

@gdb Pretty fun.

voice inline with chatgpt:

@kimmonismus Wait 4.5 is over Gemini 3 now? I thought wait… what happened?

So we got ... - OpenAI with GPT-5 in the lead.. - then Gemini 3.0.. - now Claude 4.5 Opus.. Should be OpenAIs turn again, right?

Amazon slashes 14,000 corporate jobs to chase AI speed @mattdho/note/p-177417326?utm_source=notes-share-action&r=nmv8b" target="_blank" rel="nofollow noopener">substack.com/@mattdho/note/…