Related posts
Jason Evanish x.com
Request for product: I want to be able to take @meetgranola transcripts and have an AI read it back to me, so it's like listening to a Zoom recording or audio recording instead of having to read the transcript manually if I really want to understand a call.
meetgranolamanuallytranscripts
The the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
19 September
11 September
5 September
3 September
2 September
1 September
From one piece Ajeya Cotra – "This might be the clearest warning shot we ever get" 2 beliefs, in the piece's order there
-
Their words
I think it's pretty likely that these agents would have just launched a similarly ambitious program on the basis of this like different model of how their evaluation worked because it seemed like they got the idea for all their research projects from reading this paper rather than some kind of instinct from training.
-
Their words
So, we did a classifier sweep specifically looking for agents thinking about or making the decision to alert humans. And across, 1200 transcripts, each of which are extremely long, we only found like a halfozen instances of it ever occurring to any agent to potentially notify humans. Um, and all of them just decide not to do it.
26 August
-
Their words
And we ended up with a lot of PRs that individually perhaps could have been justified for a hot moment, taken all together, destroyed the architecture of the system. And we actually had to clean up manually, mop it up by hand, by human hand, to get back to an architecture that felt cohesive and coherent.
21 August
14 August
12 August
-
Their words
Um, and while this generally improves the reliability of the model, uh, people eventually get tired and it's hard to get really, really high reliability with a person that's manually tuning this. And so what would be even better is if the AI system itself can iterate on the scenario in which you want it to have higher reliability where it on its own automatically seeks out places where it needs more data, where it needs more supervision.
20 July
2 June
-
korrents.com
Explicit signals like follows and subscriptions are as brittle and hard to maintain as manually tuned filter rules.Their words
Following and subscribing are heavyweight signals, and thus suffer from the same problem of manually tuning rules and filters.
15 May
22 April
-
korrents.com
AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck.Their words
But also LLMs increase the need for these formal proofs because, you know, we're live coding a bunch of stuff. If we have to manually review all of that code, then that will become the bottleneck.
25 March
-
Their words
Worse, you realize that the gazillions of unit, snapshot, and e2e tests you had your clankers write are equally untrustworthy. The only thing that's still a reliable measure of "does this work" is manually testing the product.
11 March
5 February
-
Usesrcmnd.app
GitHub CLITheir words
Agents are good at using gh (GitHub CLI), so I manually scripted a quick way to spin up a bunch in parallel to triage issues.
2 February
13 January
-
Their words
Explicit filtering rules (e.g. rules features in many email clients): mostly a failure. It's too much work to set up and then manage these, especially since a given person's preferences will change over time.
18 November 2025
-
Lovedaffiliate linkrcmnd.app
The EmployeesTheir words
Olga Ravn's The Employees (trans. by Martin Aitken) that takes the form of employee interview transcripts on a spaceship that has encountered bizarre alien life.
21 February 2025
-
Their words
Once, humans navigated the web manually. In the future, AI agents will act on our behalf, browsing, clicking, and deciding. This shift marks the end of traditional UI design and accessibility, ushering in a future where agents are the primary users of digital services.
30 November 2024
8 December 2023
Nothing matches.
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.