They test it on launch day, then benchmark it against that. A deviation of above 10% is considered a change. They're currently tracking Opus 5.5 and GPT-6 Astra.
This bench famously detected a degradation of Opus 4.6 which Anthropic later blogged about. I personally think people sense nerfs more often than they happen and that it's often about honeymoon effects.
Or rather it's being.. Unsubstantiated. The Nerf conspiracy isn't that there have been a few harness and platform bugs leading to performance regressions, but that OpenAI/Anthropic have maliciously and unethically degraded their model performance post release to shed load and save money.
Yeah it's just inconceivable that companies whose entire business model started by engaging in wholesale for-profit theft and abuse of intellectual property would ever be so unethical as to try to lower their costs, especially just prior to an IPO.
Again, these things are constantly measured. They sell HEAPS through their API access to enterprise consumers that expect a model to not be nerfed after it's released. And you bet many of those enterprises, some spending many millions each month, are measuring this shit.
So this is a case of extraordinary claims requiring extraordinary evidence.
And even though it's super straight forward to collect the evidence, there seems to be zero substantiating the vibe bro conspiracy theories.
> And even though it's super straight forward to collect the evidence, there seems to be zero substantiating the vibe bro conspiracy theories.
Until shit like this: <a href="https://www.anthropic.com/engineering/april-23-postmortem" rel="nofollow">https://www.anthropic.com/engineering/april-23-postmortem
Where people pointed out issues early and en masse, and Anthropic denied it was happening, gaslighted anyone claiming this was an issue, then begrudgingly admitted it was an issue, and then spent another two weeks "fixing it".
Or shit like this: <a href="https://www.anthropic.com/engineering/a-postmortem-of-three-recent-issues" rel="nofollow">https://www.anthropic.com/engineering/a-postmortem-of-three-...
Anthropic is in a perpetual state of "oops, these 'bugs' degraded our model quality" and only admit the issues when it's immediately obvious and visibly affects a large number of customers.
Otherwise all open benchmarks can be (and are) gamed. And it's quite hard to judge the output of a non-determenistic black box that Anthropic (or OpenAI) constantly tweak.
jug · · focus · HN ↗
<a href="https://www.bridgebench.ai/nerf-bench" rel="nofollow">https://www.bridgebench.ai/nerf-bench
They test it on launch day, then benchmark it against that. A deviation of above 10% is considered a change. They're currently tracking Opus 5.5 and GPT-6 Astra.
This bench famously detected a degradation of Opus 4.6 which Anthropic later blogged about. I personally think people sense nerfs more often than they happen and that it's often about honeymoon effects.
Rapzid · · focus · HN ↗
Of course it's almost entirely unsubstantiated BS.
fbrncci · · focus · HN ↗
Rapzid · · focus · HN ↗
somenameforme · · focus · HN ↗
Rapzid · · focus · HN ↗
So this is a case of extraordinary claims requiring extraordinary evidence.
And even though it's super straight forward to collect the evidence, there seems to be zero substantiating the vibe bro conspiracy theories.
troupo · · focus · HN ↗
Until shit like this: <a href="https://www.anthropic.com/engineering/april-23-postmortem" rel="nofollow">https://www.anthropic.com/engineering/april-23-postmortem
Where people pointed out issues early and en masse, and Anthropic denied it was happening, gaslighted anyone claiming this was an issue, then begrudgingly admitted it was an issue, and then spent another two weeks "fixing it".
Or shit like this: <a href="https://www.anthropic.com/engineering/a-postmortem-of-three-recent-issues" rel="nofollow">https://www.anthropic.com/engineering/a-postmortem-of-three-...
Anthropic is in a perpetual state of "oops, these 'bugs' degraded our model quality" and only admit the issues when it's immediately obvious and visibly affects a large number of customers.
Otherwise all open benchmarks can be (and are) gamed. And it's quite hard to judge the output of a non-determenistic black box that Anthropic (or OpenAI) constantly tweak.