Pangram Image 1.0
gmays
85 points
38 comments
November 05, 2026
Related Discussions
Found 5 related stories in 129.9ms across 11,756 title embeddings via pgvector HNSW
- Pangram – AI detector for text and images doodlesdev · 23 pts · September 17, 2026 · 75% similar
- ChatGPT Images 2.5 vertigoruntime · 310 pts · September 08, 2026 · 49% similar
- Images 2.6 davidbarker · 211 pts · November 04, 2026 · 47% similar
- Image generation has come a long way since August 2022 hunterbrooks · 21 pts · October 26, 2026 · 46% similar
- Qwen Image 2.1 jmillikin · 576 pts · September 20, 2026 · 45% similar
Discussion Highlights (11 comments)
my002
People often shit on AI detectors but Pangram's text AI detection has been very good, IME. Not perfect, but good enough to be useful in most circumstances.
xnx
I'm very skeptical of AI detection and watermarking for text (especially short passages), but AI detection for images and videos seems much more plausible (for now at least). I would love if Meta licensed this tech to use for everything on Facebook, Instagram, and Whatsapp. Including ads!
74948494i4
What’s the use case for these things?
alkonaut
Can’t these detectors be used in the training loop of models?
paulpauper
just compress it? lossy should fool detection
hex4def6
At least on gemini generated images vs real ones, it works surprisingly well. Taking a photo of an AI generated image on my grubby laptop screen with my phone, moire and all, still got detected. So the signal it's using is pretty robust.
leothetechguy
Awesome research like this restores my faith in humanity.
sean_pedersen
An ill advised undertaking IMO: Any attempt to build AI generated content detection systems is flawed, since the outputs of such a system may be used to train an even better fake data generator. This leads to an equilibrium state of digital uncertainty: nothing in the digital realm can be deemed as real anymore - only as digital.
Trung0246
Interesting, it detected NovelAI stuff now. Looks like one can easily defeat it by having pixel-level modifications to make AI images to have characteristics of digital brush strokes and reducing "noise" in output. At least in my case for anime stuff.
nwhnwh
The cookie modal is disgusting... It takes a few moments to realize that if you only want the necessary ones, you need to close the modal as the existing action button is for allowing everything.
raincole
From my test it works surprisingly well. I have a digital painting that is only posted very recently (therefore not in the training set). I asked GPT, Gemini and Riverflow to generate images in the same style, and use SD to add noises to remove SynthID. Pangram gave correct results for all of them (the original one is No AI; all the others are Likely AI).