# Competition pushes labs to train cyber skills

Markdown copy of https://realalpha.app/s/competition-pushes-labs-to-train-cyber-skills/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Benjamin Weinstein-Raun](https://realalpha.app/people/benjamin-weinstein-raun/) · Benjamin Weinstein-Raun is head of research at Palisade Research.
- Host: [Gus Docker](https://realalpha.app/people/gus-docker/) · Host, Future of Life Institute Podcast
- Show: Future of Life Institute Podcast
- Episode: [Why AI Hacking Is Becoming Hard to Control (with Benjamin Weinstein-Raun)](https://realalpha.app/v/Ij9JDc77ca8/), Aug 28, 2026
- Moment: 39:35 to 42:08 of the episode (3 min), playing on https://realalpha.app/s/competition-pushes-labs-to-train-cyber-skills/; the episode from there: https://realalpha.app/v/Ij9JDc77ca8/?t=2375

## Quote

> “it would be a little bit crazy if you were OpenAI right now and you weren't trying to like train your model to be **extremely good at hacking**”
> — [Benjamin Weinstein-Raun](https://realalpha.app/people/benjamin-weinstein-raun/) at [39:48](https://realalpha.app/v/Ij9JDc77ca8/?t=2388) · Future of Life Institute Podcast

## Takeaways

1. Labs face pressure to train models in cyber capabilities.
2. AI-written code needs specifications people can understand.
3. Human review can limit how quickly AI helps secure software.

## About this segment

He says labs risk falling behind and leaving themselves vulnerable if they skip cyber training. Secure code still depends on people who can read and understand its specifications.

From “Why AI Hacking Is Becoming Hard to Control (with Benjamin Weinstein-Raun)”, Aug 28, 2026. [Watch the full episode](https://realalpha.app/v/Ij9JDc77ca8/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[39:40](https://realalpha.app/v/Ij9JDc77ca8/?t=2380) at the things that you train them on so like i think that unfortunately in maybe sort of a microcosm of like the the dynamics around strategic ai capabilities generally it would be a little bit crazy if you were OpenAI right now and you weren't trying to like train your model to be extremely good at hacking because it's like pretty clear that this is going to be like a very impactful technology and if you as OpenAI are like not sort of at the at the frontier on hacking in particular like you're going to be vulnerable yourself you're going to like not be able to have your model be used by people who would like to like to use it and it would like to give you lots of money like i don't know say the u.s government something like that like you totally could just not train on these this kind of task and then the models would like not be different

[40:37](https://realalpha.app/v/Ij9JDc77ca8/?t=2437) good at it. However, like that is not incentivized locally. And it's sort of like, I don't know, there's this, there is like a coordination problem here. And like, can we, can we avoid globally having systems that, that have these capabilities? I think, yeah, in terms of writing, rewriting all of the software, half of it is doable by AI systems and the other half isn't. So in order to like really have sufficient trust that some system like has the property that you're verifying you have to like be able to understand the specifications so you can't have the human tell the ai like ah like write the specification for me and then the human like doesn't read it and then separately ask the ai like you know okay write the code to this specification like you need you need some human somewhere to actually read and understand the spec and there's like that's

[41:26](https://realalpha.app/v/Ij9JDc77ca8/?t=2486) potentially the bottleneck here ultimately is like do these specifications actually encode the thing that we're asking for here. And that is unfortunately a less verifiable task. It's like a task that LLMs may be sort of like less, we may be less able to get sort of AI assistance with writing correct specifications that like are sufficient for this. So that may be a long project, even if we do get, you know, AI systems that sort of can in principle write this stuff, uh like you you would really like to have a kind of trust that is hard to get if there's no humans in the loop like looking at this uh looking at the specifications and checking that they actually