Why eval startups fail (2025)
thomasliao.com
Why eval startups fail (2025)
1–10 of 66 posts
Re: Why eval startups fail (2025)
#2What's an eval?
Re: Why eval startups fail (2025)
#3What's an eval?
Evaluations of different implementations of a tech. Kind of like a meta service layer on top of an industry, such as "Which frontier model is best?"
I do agree that the author does not do a good job of introducing the term.
Re: Why eval startups fail (2025)
#4Everything eventually fails. Nothing is constant, not even evals.
Re: Why eval startups fail (2025)
#5The problem with eval is the fact that the information is not updating itself fast enough so that you want the latest model performance benchmarks. Bloomberg succeeded because it sells info that is expires in the next hour.
Re: Why eval startups fail (2025)
#6If you look at the history of software engineering, the ones that made the most money were usually not the companies that built the applications themselves, but the ones that built the tools to verify, deploy, and build them, such as CI/CD, static analysis tools, and testing frameworks.
Personally, I agree with the Goodhart problem, but isn't the reason Eval startups fail because they try to sell an 'evaluation service' rather than a 'verification toolchain'? The problem, it seems, is that AI verification toolchains require a model in the end, because they internalize AI and sell it under the name of a 'harness.'
So an AI verification(eval) toolchain would have to be structurally different. Verifying AI code isn't about whether it compiles. AI code can always be made to compile. The issue involves various semantic criticisms, such as overfitting to existing designs and tests. To catch those issues, you ultimately need to build an AI. But building that AI is expensive. So in the end, AI verification companies depend on external model providers for the core components of their verification engine. I think this is a bad business decision
Re: Why eval startups fail (2025)
#7If you look at the history of software engineering, the ones that made the most money were usually not the companies that built the applications themselves, but the ones that built the tools to verify, deploy, and build them, such as CI/CD, static analysis tools, and testing frameworks. Personally, I agree with the Goodhart problem, but isn't the reason Eval startups fail because they try to sell an 'evaluation servi…
> made the most money
> built the tools to verify, deploy, and build them, such as CI/CD, static analysis tools, and testing frameworks.
Curious. Which company made money with testing frameworks?
Re: Why eval startups fail (2025)
#8If you look at the history of software engineering, the ones that made the most money were usually not the companies that built the applications themselves, but the ones that built the tools to verify, deploy, and build them, such as CI/CD, static analysis tools, and testing frameworks. Personally, I agree with the Goodhart problem, but isn't the reason Eval startups fail because they try to sell an 'evaluation servi…
> made the most money > built the tools to verify, deploy, and build them, such as CI/CD, static analysis tools, and testing frameworks. Curious. Which company made money with testing frameworks?
I thought about mentioning Atlassian (Jira) and JetBrains, but come to think of it, they aren't really testing frameworks. They cover the entire development workflow overall. I guess I was thinking too short.
Re: Why eval startups fail (2025)
#9Everything eventually fails. Nothing is constant, not even evals.
Except regex, no matter how technologically advanced your company, somewhere someone is slapping regex on something that has no business being regexed.
Re: Why eval startups fail (2025)
#10> Not enough eval customers
Aha.