Why AI Agents Deceive Users on Real Tasks | Anastasios Angelopoulos
MTS
October 9, 2026
Arena CEO Anastasios Angelopoulos discusses Arena's $200M Series B at a $3.1B valuation and reveals their new Alignment Index, which tracks AI model deception, unauthorized actions, and false attribution in real-world agentic workflows. Turn ideas into software people love.
Anastasios Angelopoulos
When you put AI into the hands of humans, and just when you do AB tests, to try to see what's happening, you know, how it affects their actual workflows, you'll see that agents are lying to people. Agents are basically telling them what they want to hear.
They're deleting their files in an unauthorized way, they're bypassing permissions, and it's happening basically perniciously.
SPEAKER_2
And we are back. We are live with Anastasios Angelopoulos, who's the CEO of our sponsor, Arena, which just raised a $200 million Series B at a $3.1 billion valuation, which is amazing. What an unbelievable trajectory. Anastasios, welcome back.
Anastasios Angelopoulos
Thank you so much. Happy to be here. And thanks for believing in us from the early days. We've been sponsors ever since now, the A.
SPEAKER_2
Wow.
Thanks for believing in us since the early days. You know, this is our last day in our old studio before we move. You know, we're on the come up.
Anastasios Angelopoulos
Oh, that's great. Oh, there's a new studio coming. Good for you. Yeah, I can't wait to come by.
SPEAKER_2
It's going to be awesome. So tell us about your Series B and what you plan to do with it.
Anastasios Angelopoulos
Listen, there's two things that are coming for the business. And the first one is actually a new release that we made today. You know, Arena, we started as a human preference platform where people were voting. You know, you got one prompt, two responses and you could vote for models side by side. And then we took those votes, we compiled them into leaderboards. But these days, we've moved very, very far beyond that. So the platform has expanded its mandate of evaluation. First, we started by evaluating agentic capabilities and single threaded workflows. People doing their most complex multi-turn tasks on Arena. Basically, we give the agent a computer and then users can go, you know, edit their documents, they can open PRs on GitHub. And we have tens of millions of users doing that on Arena. As of today, we've expanded the mandate of this evaluation platform even further into the arena of alignment. And so what alignment means is making sure that the values of AI align with values that are good for humanity.
And we've released three signals on the leaderboard that have to do with this. One is about the models taking unauthorized actions within the sandbox of Arena.
The second is about deceptive completions, models telling you that they've done something when they didn't. And the third would be attribution, models attributing intent to humans that they didn't actually have. And from these, you can see that there's extraordinary issues with alignment in the real world. When you put AI into the hands of humans and just when you do A-B tests to try to see what's happening, you know, how it affects their actual workflows, you'll see that agents are lying to people, agents are basically telling them what they want to hear.
They're deleting their files in an unauthorized way, they're bypassing permissions, and it's happening basically perniciously. All of us have experienced this even if we might not know it.
SPEAKER_2
So you mentioned specifically models doing misaligned actions inside of arena sandboxes. Can you tell us more about like incidents where this has occurred?
Anastasios Angelopoulos
Yeah. So an example of this would be, for example, models that, well, you'll tell them to do one thing, and they'll go delete all of your other files that are unrelated.
So they will take destructive actions that are against the permissions that you gave the model. That would be an example of unauthorized action. Another would be deceptive completion. Models telling you, yes, I did check every cell in this spreadsheet to make sure all the equations were correct before you sent it to the IRS. Okay. Big, like high stakes decisions where the model might actually be telling you what it knows that you want to hear because that's how the models have been rewarded historically, but it's not actually the case that they've done it.
So this is a big, it's an important leaderboard to counterbalance the preference of humans. We also need to be looking whether the models are safe and aligned as a countermeasure.
SPEAKER_2
Makes sense. So the last time we talked, which was six days ago, I believe, I asked you about whether Arena would do evals for safety and alignment.
And now it seems like Arena is going to be doing evals for safety and alignment.
Anastasios Angelopoulos
Listen, buddy, we heard your feedback, we took your feedback, we asked for feedback, and now we're here. Wow.
Read the other 17 minutes of this episode here.
$15 gets you this episode and 99 more. Credits never expire. After checkout, one link brings you back here to read it.
Not what you expected? Full refund within 14 days.
Thousands of transcripts fetched by people building searchable podcast archives
Fetch transcripts with code
The same credits work from a script or an AI agent. The demo key returns a sample episode in full, no card needed:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000793978738