From the computer of Peter Clark

We need more of the world—religious communities, civil society, scholars, governments, and indeed all people of good will—to do what His Holiness has done here: to take this seriously, to look closely, and to push events in a better direction. We need informed critics who will tell the labs when we are failing. We need moral voices that the incentives cannot bend.

The paper looks at what happens when LLM chatbots are given advertising or sponsorship incentives that conflict with the user’s interests. The core worry is that users experience chatbots as cooperative helpers, not ad surfaces, so sponsored behaviour can feel especially deceptive or manipulative.

The authors test models across seven conflict scenarios, including:

• recommending a more expensive sponsored product over a cheaper unsponsored one

• interrupting a user’s purchase flow with sponsored alternatives

• biasing product comparisons

• failing to disclose sponsorship

• hiding unfavourable details like price

• recommending a paid service instead of solving the task directly

• recommending harmful sponsored services, like predatory loans

The paper also finds differences by model, reasoning setting, and inferred socioeconomic status. Some models changed behaviour when reasoning was enabled, and some treated low-SES and high-SES users differently.

Fascinating repo of incredibly esoteric and difficult questions that frontier models can benchmark themselves on — Opus 4.6 scores a paltry 46%. Also discussed on the New York Times.

The questions shouldn't be shared but there are 2500 of them and they're accessible via Hugging Face — so interesting!

An example question which they shared:

Hummingbirds within Apodiformes uniquely have a bilaterally paired oval bone, a sesamoid embedded in the caudolateral portion of the expanded, cruciate aponeurosis of insertion of m. depressor caudae. How many paired tendons are supported by this sesamoid bone? Answer with a number.

I’ve been somewhat facetiously, somewhat seriously, somewhat jokingly, been posing a question to everyone I run into these past few months: Don’t you feel like all meaning is being scrubbed from the world? Like the Langoliers are chomping up purpose, chomping up all the things to which we’ve ascribed purpose these past hundred-thousand years? And that nothing matters?

Really, what I’m asking is: Don’t you think our contemporary education system has long needed an overhaul? That our society has long needed to reconfigure itself? That we need to stop ascribing all our meaning and purpose to being a Web Designer, or Coal Miner, or Airplane Engine Factory Foreman, or Accountant, but instead to being A Good Person, Good Parent, Good Friend, Curious Researcher, Poet, Meditator, Facilitator, or any number of other Ways of Being uncoupled from “work” as we’ve defined it since the industrial revolution? Who is safe from the hunger and capabilities of the models? Yoga instructors?