# One-Pager Brief on Pangram Labs

> Source: <https://www.lesswrong.com/posts/gcbTXSpENASM8xfWf/one-pager-brief-on-pangram-labs>
> Published: 2026-07-12 18:36:11+00:00

Pangram Labs builds the most accurate AI text detector in the world. Team is >25 FTE; they are active on Twitter, you can engage directly, look for "affiliates" tab of @pangram.

Here is a table of their performance on adversarially modified AI text ([source paper](https://arxiv.org/abs/2501.03437)):

Language | AI Text Detection % | Humanized AI Text Detection % |
|---|---|---|
GPTZero | 95.60% | 34.53% |
Binoculars | 94.40% | 29.73% |
Pangram Baseline | 100.00% | 73.07% |
Pangram Humanizers | 100.00% | 93.66% |

Note that "*current model!*" is not current as of July 2026. Their classifier now provides a percentage instead of a binary verdict. They released an [open source model](https://huggingface.co/pangram/editlens_Llama-3.2-3B) (Llama-3.2-3B QLoRA) which was SOTA at the time. The paper does not test adversarially modified AI text, but you are welcome to try running this test ([repo](https://github.com/sheikheddy/EditLens/)); it may trigger agent safeguards.

Note again that "Pangram" in this table is not current as of July 2026. Their [production model](https://www.pangram.com/research/model-card/pangram-3-3) detects Fable 5 outputs with 99.64% accuracy ([blog](https://www.pangram.com/blog/does-pangram-work-on-claude-fable-5)). See [prompts](https://docs.google.com/spreadsheets/d/1ZgMEj238f0jpWpY3TQTcJzNuL6RK6pEIqBjuug7gVHw/edit?usp=sharing). Reasoning effort level (High, Max, etc) is not disclosed. Just to be clear, Pangram knows that the output came from *some* AI model, but their technology does not predict the specific model used.

Pangram Labs has announced plans to open a Toronto office later this year. I expect that Pangram's business will grow faster than the following AI companies with offices in Ontario: Ideogram, Elevenlabs, Cerebras, Cognichip, Decagon, and Cohere. I lack sufficient information to forecast their ultimate size. Pangram's Chrome extension has ~10k users, I would upper bound this at ~50m if they can maintain their leader position.

If I had to guess, the frontier lab most likely to acquire them is Thinking Machines, based on the premise that we primarily care about the provenance of text when humans will read it. If the target is a machine and not a human, the content of the payload matters more than its origin (I am open to changing my mind about this point upon discussion).

Detection is the first step in mitigating security threats, so initially, better detectors sound great. But evasion co-evolves with detection. Currently, humans can easily detect AI text. But if Pangram succeeds (operating as a filter on most text shown to humans in environments where LLM text is excluded), this may no longer be the case, and we may become dependent on AIs for accurate AI text detection sooner. It is not guaranteed that natural text will be trusted text, but LLM generated text is more likely to be unsafe in cases where many egregiously misaligned AIs are hostile to humanity without being strong enough to take over. AI verification is an important prerequisite for an agreement in [Plan 2040](https://ai-2040.com/), but I haven't thought about whether AI text detection counts.