YOLO object detection model
Hacker ApprovedObject detection model in AI tools
Fast, accurate object detection that works with little training data and modest hardware. Critics question Ultralytics' AGPL licensing and say newer versions are less open.
Fast, accurate object detection that works with little training data and modest hardware. Critics question Ultralytics' AGPL licensing and say newer versions are less open.
28 people gave an opinion
- recommend it
- 19
- criticize it
- 9
- approval share
- 68%
Recommended in 8 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 19 people recommend itNeeds 10 or more, met.
- 2.1 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 8 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Fast real-time inference on modest hardware
“For realtime on the edge the YOLO series is pretty good, I don't think anyone would disagree.”
Comment from 27 Feb 2026 in “Palantir's AI Is Playing a Major Role in Tracking Gaza Aid Deliveries” “you don't need a lot of GPU power to do say YOLOv8 inference on the pre-trained models”
Comment from 16 Dec 2025 in “alpr.watch” “if I want to do that faster/cheaper/at 60fps then I should be using yolo or similar”
Comment from 7 Oct 2026 in “Decisions API is in public beta” - Comment from 9 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision”
Strong results from pretrained, fine-tuned models
“The yolo models are really shockingly good for their cost and how well they can work with not much training data as well.”
Comment from 9 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision” “I would suggest YOLO. Depending on your domain, you might also finetune these models.”
Comment from 25 Nov 2025 in “Meta Segment Anything Model 3” “I can get great results from a YOLO model with 30M to maybe 300M params.”
Comment from 9 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision” - Comment from 9 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision”
Reliable for many use cases
“YOLO has basically solved that for my use cases for a couple years now”
Comment from 9 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision” “YOLO is a good example for something that can work.”
Comment from 15 Mar 2026 in “$96 3D-printed rocket that recalculates its mid-air trajectory using a $5 sensor” “yolo/ssd work good for this”
Comment from 9 Nov 2025 in “The overengineered solution to my pigeon problem (2022)” Practical alternative to LLM vision
“if I want to do that faster/cheaper/at 60fps then I should be using yolo or similar”
Comment from 7 Oct 2026 in “Decisions API is in public beta” “I suggested YOLO and non llm-vl as a lot faster alternative.”
Comment from 25 Nov 2025 in “Meta Segment Anything Model 3”
What people warn about
Each mark is one comment
Ultralytics AGPL licensing concerns
“Ultralytics then created their own model under the AGPL-3.0 license, which probably would never stand up in a court as they have the model from the likes of YOLOv3 in their source”
Comment from 22 Nov 2025 in “Why DETRs are replacing YOLOs for real-time object detection” “given their aggressive approach to licensing, I can't imagine why anyone would choose to use an Ultralytics model on a new project in 2026”
Comment from 23 Jun 2026 in “An Introduction to YOLO26” “which probably would never stand up in a court as they have the model”
Comment from 22 Nov 2025 in “Why DETRs are replacing YOLOs for real-time object detection” - Comment from 14 Jun 2026 in “Show HN: Dual YOLOv8n UAV Detection on RK3588S at 42 FPS Using NPU”
- Comment from 23 Jun 2026 in “An Introduction to YOLO26”
Performance disappointing in some tests
“was quite disappointed in how it performed”
Comment from 23 Jun 2026 in “An Introduction to YOLO26” “even with a fancy YOLO model these answers get thrown out in 1.5-50ms”
Comment from 6 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision” Costly commercial licensing
“given their aggressive approach to licensing, I can't imagine why anyone would choose to use an Ultralytics model on a new project in 2026”
Comment from 23 Jun 2026 in “An Introduction to YOLO26” “When we came to productionisation ultralytics wanted $$$”
Comment from 22 Nov 2025 in “Why DETRs are replacing YOLOs for real-time object detection” Seen as overkill or outdated
“I believe that using YOLO and other methods is outdated.”
Comment from 6 Jun 2026 in “OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision” “YOLO is overkill for basic weed/crop discrimination”
Comment from 24 Feb 2026 in “Show HN: Sowbot – open-hardware agricultural robot (ROS2, RTK GPS)”
What people recommend instead
The same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| YOLO object detection modelThis page | 19 | 9 | 68% | 8 | — | Approved |
| Ultralytics YOLO26 | 6 | 3 | 67% | 1 | — | — |
What people said
All 31 comments that mention it, newest first. Each links to the original comment.
“if I want to do that faster/cheaper/at 60fps then I should be using yolo or similar”
“given their aggressive approach to licensing, I can't imagine why anyone would choose to use an Ultralytics model on a new project in 2026”
“was quite disappointed in how it performed”
“pushing AGPL in a very overreaching way with their models”
“any practical improvements were between all of the spinoff models”
“have shown it to be effective for terminal guidance”
“Newer versions aren't open source, or at least have murky licencing.”
“Training YOLO takes a few hours and is then very fast.”
“The yolo models are really shockingly good for their cost and how well they can work with not much training data as well.”
“I can get great results from a YOLO model with 30M to maybe 300M params.”
“YOLO has basically solved that for my use cases for a couple years now”
“running a mildly fine-tuned YOLO doing local-only object detection”
“There's a time and place for more "traditional" computer vision methods.”
“even with a fancy YOLO model these answers get thrown out in 1.5-50ms”
“I believe that using YOLO and other methods is outdated.”
“This is rad I've been looking for something exactly like this.”
“it's been enough to make me feel better about running agents with fewer guardrails”
“Love that YOLO has a cat class.”
“YOLO is a good example for something that can work.”
“For realtime on the edge the YOLO series is pretty good, I don't think anyone would disagree.”
“YOLO is overkill for basic weed/crop discrimination”
“It needed a lot a human validation but was so fun.”
“you don't need a lot of GPU power to do say YOLOv8 inference on the pre-trained models”
“I suggested YOLO and non llm-vl as a lot faster alternative.”
“they are easy to use and you can just benchmark them yourself”
“I would suggest YOLO. Depending on your domain, you might also finetune these models.”
“which probably would never stand up in a court as they have the model”
“Ultralytics then created their own model under the AGPL-3.0 license, which probably would never stand up in a court as they have the model from the likes of YOLOv3 in their source”
“This article is a total scam, it should be removed.”
“When we came to productionisation ultralytics wanted $$$”
“yolo/ssd work good for this”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.