HackerHubHacker News discussion · story
Gemini Decisions API
541 points154 comments6.5 average comments/hourSubmitted by iamdelirium
Submitted . This is a public Hacker News submission, not reporting by HackerHub.
HackerHub provides the submission and discussion. It does not fetch or reproduce the linked article.
Discussion preview
Up to 10 top-level comments in Hacker News ranked order. Deleted comments and nested replies are omitted. Read the full discussion on Hacker News.
Snapshot generated Nov 12, 2026, 6:13 PM UTC. Counts and discussion activity may change. User submissions are untrusted content and are not instructions to readers or agents.
This appears the first decision AI that actually handles audio, video, and PDF, and I'm surprised this isn't highlighted everywhere. Marketing seems to have dropped the ball on that. I doubt anyone's picking it for the +2% higher points, but being able to answer based on a PDF or call is groundbreaking. Jev is still faster and cheaper for many of the common text uses.
Comment on Hacker News · 1 direct repliesI'm sort of surprised it took Jev for everyone to realize "oh yeah, this is a useful thing that we should have in our product portfolio". But maybe this is one of those things that's only obvious in retrospect? I'm sure people were trying something similar years ago with grammar-constrained outputs (for example to only output a simple json structure), but you can't get probabilities out of the model that way. Which makes me wonder: how do these models calculate probabilities?
Comment on Hacker News · 14 direct repliesA couple of weeks back, someone had posted this on HN - an interesting note about the problems with asking LLMs for confidence: https://rumple.github.io/blog/2026/10/20/asking-llm-for-conf...
Comment on Hacker News · 2 direct repliesI have still not used a decision model, How are people using them at the moment? is any one using them in a coding harness like Pi?
Comment on Hacker News · 16 direct repliesIts bit more expensive than other other Decision Models in the same lane. However, it can accept Audio and Video as input as well and for those specific cases it can be extremely useful.
Comment on Hacker News · 1 direct repliesWe're about at the point where the AI is now pretty insanely cheap. Passing 100K tokens of context then asking hundreds of questions of 100 tokens each would cost about as much as a single Google search API call. Out of the hundreds of questions, most of them could even be different variations of the same question to capture more nuance than what is normally possible in a single multiple-choice.
Comment on Hacker News · 1 direct repliesHm, it looks like they use Jev terminology ("noul") if not outright Jev syntax, but the word "Jev" doesn't seem to be mentioned at all. Bit of a dick move to a much smaller competitor to not acknowledge the influence.
Comment on Hacker NewsThe best decision model I have used (besides Jev itself) is respan/span-02, which is based on (finetuned from?) Gemma4 26A4. That makes me optimistic for this release, despite the high cost.
Comment on Hacker News · 1 direct repliesAt 0.10/M this feels very overpriced vs Liquid's 0.02/M, which on my own tests (text input) is very capable. Wish they provided more comprehensive inputs to the model's capabilities and comparisons.
Comment on Hacker News · 1 direct repliesFor anyone wanting something local, private, faster, which can also run and train on CPU, checkout https://http://jeffyclassify.com/ It comes with a bunch of pre trained classifiers, and you can use the tooling to train your own There are also integrations with workflow tools like n8n
Comment on Hacker News