The Model You Love Is Probably Just the One You Use

Ask 10 developers which large language model (LLM) they’d recommend, and you’ll get 10 different answers—and almost none of them are based on objective comparison. What you’ll get instead is a reflection of the models they happen to have access to, the ones their employer approved, and the ones that influencers they follow have been quietly paid to promote. We’re all living inside recursively nested walled gardens, and most of us don’t realize it.

The access problem

In corporate environments, the model selection often happens by accident. Someone on the team tries Claude Code one weekend, gets excited, tells the group on Slack, and suddenly the whole organization is using it. Nobody evaluated alternatives. Nobody ran a bakeoff. The decision was made by whoever had a company card and a free Saturday. That’s not a criticism—it’s just how these things go. But it means that when that same person tells you their favorite model, they’re really telling you which model they’ve had the most reps with. There’s a genuine learning function at play: You get faster, your prompts get better, and the model starts to feel almost intuitive. It’s not that the model is objectively superior. It’s that you’ve gotten good at using it.

This matters more than people admit, because a lot of this space runs on feelings rather than evidence. People feel good about Opus right now. It feels powerful; it feels smart; it feels like you’re using the best tool available. And maybe you are. But ask someone who’s paying for their own tokens whether they feel the same way, and you tend to get a more calibrated answer. Skin in the game has a way of sharpening opinions.

The influence problem

There’s also a lot of money moving through this space in ways that don’t always get disclosed. Model providers are spending real budget to make sure the right people have the right experiences—early access, credits, invitations to exclusive communities. These perks can create a sense of exclusivity and importance, making users more likely to champion the model they’ve been given access to.

Influencers play a significant role in shaping these dynamics. Many LLM creators partner with influencers to promote their models, often in exchange for free access or other incentives. This can lead to a skewed perception of which models are the best, as users are more likely to engage with and trust recommendations from influencers they already follow.

The result is a fragmented landscape where the models we love are often the ones we use, rather than the ones that are objectively the best. This isn’t necessarily a bad thing—different models cater to different needs and preferences—but it’s important to be aware of the factors that influence our choices.

Ultimately, the key to making informed decisions about which LLM to use lies in understanding the biases and limitations of our own experiences. By recognizing the role of access, influence, and personal bias, we can better evaluate the models at our disposal and make choices that align with our own needs and goals.

In a world where the best tool is often the one we’re most familiar with, it’s crucial to stay open to new possibilities and challenge the status quo. By doing so, we can unlock the full potential of the rapidly evolving field of large language models and harness their power to its fullest extent.