Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Affirm Retooled for Agentic Software Development in One Week

medium.com

Post reply on HN
Print view View original

21–27 of 27 posts

Re: Affirm Retooled for Agentic Software Development in One Week

#21

Post by tomwojcik »

dghlsakjg wrote: post #20
tomwojcik wrote: post #19

Earlier quoted context omitted.

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…

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.

Re: Affirm Retooled for Agentic Software Development in One Week

#22

Post by zug_zug »

> This post covers how we got to a place where over 60% of our pull requests (PRs) are agent-assisted

Well I mean you could (and should) turn on 100% agent code-reviews, and that's a type of assistance.

The hard part is that most orgs never made disposable environments nor any meaningful local testing, so the ability to validate code doesn't break something indirectly (e.g. memory leak, hammer the prod DB, cache values with the wrong key, etc) isn't there. In my experience AI code has several subtle bugs and is deceptively dangerous (because it can look so competent in other ways).

Re: Affirm Retooled for Agentic Software Development in One Week

#23

Post by giancarlostoro »

zug_zug wrote: post #22

> This post covers how we got to a place where over 60% of our pull requests (PRs) are agent-assisted Well I mean you could (and should) turn on 100% agent code-reviews, and that's a type of assistance. The hard part is that most orgs never made disposable environments nor any meaningful local testing, so the ability to validate code doesn't break something indirectly (e.g. memory leak, hammer the prod DB, cache valu…

> The hard part is that most orgs never made disposable environments nor any meaningful local testing, so the ability to validate code doesn't break something indirectly (e.g. memory leak, hammer the prod DB, cache values with the wrong key, etc) isn't there. In my experience AI code has several subtle bugs and is deceptively dangerous (because it can look so competent in other ways).

There's ways to improve on this, but nobody ever wants to invest more in disposable dev environments, dev is always the wimpiest environment of them all.

Re: Affirm Retooled for Agentic Software Development in One Week

#24

Post by visageunknown »

dghlsakjg wrote: post #20
tomwojcik wrote: post #19

Earlier quoted context omitted.

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…

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.

Re: Affirm Retooled for Agentic Software Development in One Week

#25

Post by deadbabe »

visageunknown wrote: post #24
dghlsakjg wrote: post #20

Earlier quoted context omitted.

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…

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 wh…

Do you own stock in Affirm?

Re: Affirm Retooled for Agentic Software Development in One Week

#26

Post by Eridrus »

deadbabe wrote: post #5

Affirm is on its way out anyway, so really this is one last Hail Mary to try to prop up the company, they don’t have much left to lose.

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.

Re: Affirm Retooled for Agentic Software Development in One Week

#27

Post by kevinluddy39 »

SkyPuncher wrote: post #16
ookblah wrote: post #8

having tried to wrangle this on my own over months and still seeing gaps everyday i have to raise severe skepticism on this lol. you mandate and "solve" this in a few weeks over 1:N channels and measure on a metric that nobody even fully understands yet = someone getting paid to bullshit some metrics on agentic productivity to executives. i agree with other posters, 12 months until a dumpster fire of shit reveals its…

I’m in the cutting edge of agentic dev at my company, but there’s no way they could have rolled this out in a meaningful way in two weeks. I can barely get a repeatable process, let alone one that I can actually teach everyone else. “Decide upfront” is a load of crap. I can write the “perfect” spec plan, but we always, always miss something or misunderstand something. Agents will follow a high confidence spec blindly…

[dead]
Post reply on HN