Viewing profile — dagss
dagss
HN member- Joined
- Mon, Apr 23, 2012, 7:47 PM UTC
- HN karma
- 2,032
- Public activity
- 801 items
- HN profile
- View on Hacker News ↗
About dagss
https://syncmap.com
https://www.linkedin.com/in/dag-sverre-seljebotn-84535a86
Recent public activity
-
comment
Comment #49185675
What do you mean GUI? Of course the observation of the agents behaviour happens by reading the code it emits.
-
comment
Comment #49180620
But if you observe that the agent day after day do handle user input safely; and also routinely run an agent that scans for security vulnerabilities and observe it finding cases wh…
-
comment
Comment #49138955
Even if the fake is super-fast compared to postgres (1%) in CPU resources: Why spend extra engineering effort to build something that has less fidelity? CPU for test runs is cheap.…
-
comment
Comment #49138773
If you are unit testing something then sure mock out everything you are not concerned with. But for service layer tests I don't agree with you, including the actual production repo…
-
comment
Comment #49076437
BETA: I have been following https://github.com/superradcompany/microsandbox a bit, very simple to get started with at least.
-
comment
Comment #49045203
I feel like the article is leaving the most important part out ; how to allocate that "offset" (sequence number) which allows consumers to keep tabs on how far they have read and q…
-
comment
Comment #49017642
It is downvoted because you first talk about "AI psychosis", then acknowledge the very issues people are concerned about. If our prisons are all random bricks glued together, that …
-
comment
Comment #48984986
Or to be more specific, issue isn't text/templating as such. It is a fine templating language for text. But to use a text templating language to generate YAML, which is not only st…
-
comment
Comment #48903942
Comparing changes in nuclear doctrines with people choosing a different way of life (granted, also for their children) than the majority seems totalitarian, to me. Minorities are, …
-
comment
Comment #48902961
Do you feel current western capitalistic culture is perfect and the peak of what humanity can accomplish? There should be more, not less, experiments in alternative ways of life. I…
-
comment
Comment #48824386
Of course. But I prefer IDEs that group and name the agent sessions by the worktree they are tasked with automatically.
-
comment
Comment #48823828
Claude can easily do the merges I need (or myself manually for that matter). I guess all codebases and usecases are very different here and hard to give general advice. But I do ha…
-
comment
Comment #48823713
As the sibling comments note, this is kind of off-topic to my post. But I think git worktrees are a bit more ergonomic, I don't have to think about local vs upstream there's just o…
-
comment
Comment #48823265
Is there git worktree support? With the long waits for agents to do stuff I really don't see how one can get anything done without multitasking with multiple worktrees in parallel.…
-
comment
Comment #48786864
I would argue that is a bit like complaining there is no "backend language" and that Java, Rust, Go all have different syntax. The choice of DB is arguably more important than the …
-
comment
Comment #48780991
Thank you that was clearer. So, I have a PhD in Astrophysics so I am not a total stranger to doing some thinking. And I would say "create (...) answers by relying on the abstract c…
-
comment
Comment #48780026
I didn't really try to argue that LLMs "have understanding". I am more, in a sense, arguing that "understanding" isn't clearly defined and sceptical about your confidence that this…
-
comment
Comment #48774542
Humans don't make the exact same errors of LLMs of course. Humans are very different beings. So you recognize that Claude is not a human. Humans make mistakes as well "inconsistent…
-
comment
Comment #48773295
It's the same with human intelligence though. A human can be brilliant on some things and then we're puzzled why they are so idiotic in other areas. Every time this comes up, peopl…
-
comment
Comment #48772131
The article seems to define "smart" as being good at spatial awareness and navigating a body through 3D space and such. Thus, a mice is smarter than an LLM. That's the first time i…
-
comment
Comment #48716917
I have been actively searching for such a thing for months without finding it. Some are OS X only. Some will not work well with VMs/isolated agents. Currently using emdash, which i…
-
comment
Comment #48577517
Do you have to? Is it common to treat ?a=1&b=2 the same as ?b=2&a=1 in browser/CDNs/etc? Seems the spec puts this as a MAY. I think I doubt it will be implemented in generic ways, …
- comment
-
comment
Comment #48538115
As a Norwegian teen parent: Seeing all the issues cropping up which is /enabled/ (not saying caused) by social media, you don't need to look for ulterior motives. I believe these b…
-
comment
Comment #48520401
Not sure what you mean. Whether Claude one shots or not, it spends some minutes and in those minutes I can start another task in another worktree...