It got a 62, a C+, predicting that this won't be very viral. So you either didn't test this submission on your own product, or you did, but didn't feel that the low score was a handicap? You don't seem to be dogfooding. If this post does well it would be evidence against its own accuracy. If it fizzles out, congratulations on being correct.
The analysis they ran in their research paper found most surface features don’t meaningfully separate viral from non‑viral outcomes. So the tool isn't actually predicting if your launch title will go viral, it's more like checking for heuristics and descriptive patterns.
Cool idea though! And they're on the front page lol
(Replaced my original comment here which was a little unkind.)
Question for OP, who created Memvid (the .mv2 file format that's used to distribute this data). Are you still taking text, chunking it and then storing those chunks as QR codes in a video file? That seems like an inherently inefficient storage mechanism to me compared with something like SQLite or Parquet - do you have concrete numbers or a demo that shows that your file format really is more effective for storing data for "AI agents" than those existing solutions?
Here are the result for this username, this title and this description:
https://hn-ph.vercel.app/results/ZT06GF
It got a 62, a C+, predicting that this won't be very viral. So you either didn't test this submission on your own product, or you did, but didn't feel that the low score was a handicap? You don't seem to be dogfooding. If this post does well it would be evidence against its own accuracy. If it fizzles out, congratulations on being correct.
Uncharitable and assumptious of the goals. I prefer submissions to not be hyper-optimized for virality.
Current nr 3 in the leaderboard: "Show HN: I built a Rust compiler in Rust with Rust"
Could use some more Rust to boost it to nr 1.
I'm calling it: Some AI controversy in Rust core will be in the top 5 of 2026.
This tool: "Avoid keyword stuffing; make the title read naturally."
Also this tool: "Show HN (AI): I built GPT 6 in Rust Using Claude Gemini Grok OpenAI NVIDIA Google" - #1
(No hate to the creators obviously. Just really funny.)
The analysis they ran in their research paper found most surface features don’t meaningfully separate viral from non‑viral outcomes. So the tool isn't actually predicting if your launch title will go viral, it's more like checking for heuristics and descriptive patterns.
Cool idea though! And they're on the front page lol
Well, he made it to the front page so there’s that.
(Replaced my original comment here which was a little unkind.)
Question for OP, who created Memvid (the .mv2 file format that's used to distribute this data). Are you still taking text, chunking it and then storing those chunks as QR codes in a video file? That seems like an inherently inefficient storage mechanism to me compared with something like SQLite or Parquet - do you have concrete numbers or a demo that shows that your file format really is more effective for storing data for "AI agents" than those existing solutions?
Let's see if this goes viral
o7 see you in the 1% someday