maxspero
Joined 5 years ago
Karma
94
Submissions
28
Member since
Sep 15
Keeping human spaces AI-free @ pangram.com
View on Hacker NewsRecent submissions
Comment · 3 months ago
> Sounds promising, right? I spent some time trying [perplexity], but results were disappointing—plenty of false positives and false negatives, and no reasonable threshold could be set.
Perplexity was widely considered SOTA in 2022. One part of it is because everyone was evaluating on open models or closed models that were still close (i.e. GPT-2 vs. GPT-3.5). Today, the gap is so much wider between the models you can use to compute perplexity and the frontier models people actually use.
Also so many AI text detection papers used a strawman RoBERTa baseline that was very undertrained for the task.
The synthetic mirrors method for data generation used here is the same as what we use at Pangram. Good blog post, thank you for sharing!
Comment · 4 months ago
Update: this is actually ZeroBounce’s Verify+ feature which we figured out after some escalation. It’s now disabled!
Comment · 4 months ago
Follow-up: our vendors have told us that they do not send any emails as part of the validation process. Either somebody is lying, or there's something even weirder going on. We still have more tests to run to isolate which software package it could be.
Comment · 4 months ago
Hey! Founder of Pangram here. We use Zerobounce and CustomerIO for email validation. I had no idea this was happening. Not entirely sure which one this is coming from, but this is not intentional on our part. Will dig deeper and eliminate the part of the stack that is sending spam — definitely not good that this is happening.
Comment · 11 months ago
Anecdotally people are seeing a rise of low-quality reviews which is correlated with increased reviewer workload and and AI tools giving reviews an easy way out. I don't know of any studies quantifying review quality, but I would recommend checking the Peer Review Congress program from past years.
Comment · 11 months ago
It's definitely going to be a back and forth - model providers like OpenAI want their LLMs to sound human-like. But this is the battle we signed up for, and we think we're more nimble and can iterate faster to stay one step ahead of the model providers.
Comment · 11 months ago
Pangram is trained on this task as well to add additional signal during training, but it's only ~90% accurate so we don't show the prediction in public-facing results
Comment · 11 months ago
Thanks, fixed.
Comment · 11 months ago
Yeah, Pangram does not provide any concrete proof, but it confirms many people's suspicions about their reviews. But it does flag reviews for a human to take a closer look and see if the review is flawed, low-effort, or contains major hallucinations.
Comment · 11 months ago
There are dozens of first generation AI detectors and they all suck. I'm not going to defend them. Most of them use perplexity based methods, which is a decent separators of AI and human text (80-90%) but has flaws that can't be overcome and high FPRs on ESL text.
https://www.pangram.com/blog/why-perplexity-and-burstiness-f...
Pangram is fundamentally different technology, it's a large deep learning based model that is trained on hundreds of millions of human and AI examples. Some people see a dozen failed attempts at a problem as proof that the problem is impossible, but I would like to remind you that basically every major and minor technology was preceded by failed attempts.
Comment · 11 months ago
Our benchmarks of public datasets put our FPR roughly around 1 in 10,000. https://www.pangram.com/blog/all-about-false-positives-in-ai...
Find me a clean public dataset with no AI involvement and I will be happy to report Pangram's false positive rate on it.
Comment · 11 months ago
I am not sure if you are familiar with Pangram (co-founder here) but we are a group of research scientists who have made significant progress in this problem space. If your mental model of AI detectors is still GPTZero or the ones that say the declaration of independence is AI, then you probably haven't seen how much better they've gotten.
This paper by economists from the University of Chicago economists found zero false positives of 1,992 human-written documents and over 99% recall in detecting AI documents. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5407424
Comment · 11 months ago
Co-founder of Pangram here. Our false positive rate is typically around 1 in 10,000. https://www.pangram.com/blog/all-about-false-positives-in-ai....
We also wanted to quantify our EditLens model's FPR on the same domain, so we ran all of ICLR's 2022 reviews. Of 10,202 reviews, Pangram marked 10,190 as fully human, 10 as lightly AI-edited, 1 as moderately AI-edited, 1 as heavily AI-edited, and none as fully AI-generated.
That's ~1 in 1k FPR for light AI edits, 1 in 10k FPR for heavy AI edits.
Comment · 1 year ago
I've been using Grapevine at my company for the last couple weeks. One of the coolest features is that it proactively answers questions (with citations!). Not everyone thinks to tag the bot but it often surfaces the relevant answer and document and saves everyone some time.