I have no opinion on Affirm as a business, but going beyond the headline, this seems pretty unimpressive.
"over 60% of our pull requests (PRs) are agent-assisted" is a pretty low bar these days.
The off the shelf tools (Claude Code/etc) are all good enough that basically every PR should probably be LLM assisted at this point.
It's good for them that they have made progress, but "assistance" is not really at the frontier of what people are trying to get to.
The real question for software engineering is: how can we get to the point where simple prompts get to production quality code without human intervention. Human review is still ok, but we want to get getting to the point where most PRs are one shot, or with the LLM proactively asking the questions that are necessary, not the human having to repeatedly re-review the same code multiple times for quality.
Of course after that the goal is taking the hands off the wheel entirely, just purely filing tickets.
So far I think we're mostly just waiting on model improvements or accepting that the code we get is garbage, but I would love to hear people's experiences taking their hands off the wheel in production settings.
I don't have a horse in this race, but I'm curious. Could you please shed some light on why they are on their way out? I'm from Poland and they seem to keep hiring here. Afaik most of their engineering department is in Poland. At the same time, I don't understand the product as credit cards are not popular here and Affirm as a product isn't available in Poland anyway.
They loan money to people that have either bad understanding of money, or who no other lender will work with. A lot of their revenue also rely on discretionary spending on consumer goods (the kind of stuff that people stop buying first when things go badly).
They kept getting surprised by how many of their loans go unpaid on top of all that.
So they are lending to the riskiest consumers, and they kept underestimating the risk, though they might have fixed that. The past three quarters they have finally become profitable, but given their portfolio of risky consumer loans that are unsecured, any kind of economic downturn could really hurt them.
They aren’t really on their way out right now, but they are in a dangerous position if, say, some global economic event were to cause a massive economic shock…
Thank you. I think their biggest threat is rapidly rising interest rates but as you said, they are profitable currently, so I wouldn't say they will go under anytime soon.
You have no idea what you’re talking about. Affirm has some of the lowest delinquency rates of any BNPL and targets consumers that are more likely to repay their loans. In addition, the consumer spending dependency is remarkably resilient in both upturns and downturns, of course to a certain point - if we’re in a complete economic collapse affirm is not the only stock that will crater.
You seem to be speaking from what you’ve heard through social media and sheer ignorance.
"over 60% of our pull requests (PRs) are agent-assisted" is a pretty low bar these days.
The off the shelf tools (Claude Code/etc) are all good enough that basically every PR should probably be LLM assisted at this point.
It's good for them that they have made progress, but "assistance" is not really at the frontier of what people are trying to get to.
The real question for software engineering is: how can we get to the point where simple prompts get to production quality code without human intervention. Human review is still ok, but we want to get getting to the point where most PRs are one shot, or with the LLM proactively asking the questions that are necessary, not the human having to repeatedly re-review the same code multiple times for quality.
Of course after that the goal is taking the hands off the wheel entirely, just purely filing tickets.
So far I think we're mostly just waiting on model improvements or accepting that the code we get is garbage, but I would love to hear people's experiences taking their hands off the wheel in production settings.