Viewing profile — mulmboy
mulmboy
HN member- Joined
- Tue, Jan 12, 2021, 10:54 AM UTC
- HN karma
- 250
- Public activity
- 111 items
- HN profile
- View on Hacker News ↗
About mulmboy
Recent public activity
-
comment
Comment #48898612
I went to build an open source app from GitHub and was pretty surprised that it requires Xcode and that Xcode can't really be installed without an apple id. I do not want to make o…
-
comment
Comment #48879377
Very difficult to take seriously when the entire site appears to be AI-written.
-
comment
Comment #48864967
There's a cluster of issues like comments like "use a set instead of ..." after changing something which will just confuse people in the future. Or comments referring to irrelevant…
-
comment
Comment #47680693
There are a few hints in the doc around this > Importantly, we find that when used in an interactive, synchronous, “hands-on-keyboard” pattern, the benefits of the model were less …
-
comment
Comment #46773759
What I'm saying is that a corporate or professional environment can make people communicate in weird ways due to various incentives. Reading into people's communication is an impor…
-
comment
Comment #46770448
People more often say that to save face by implying the issue you identified would be reasonable for the author to miss because it's subtle or tricky or whatever. It's often a prox…
-
comment
Comment #46763519
Because it's a good heuristic for a functional and resilient team. People don't usually means it literally, more like "if I disappeared it should be pretty painless for the team to…
-
comment
Comment #46664216
LLMs aren't like you or me. They can comprehend large quantities of code quickly and piece things together easily from scattered fragments. so go to reference etc become much less …
-
comment
Comment #46462247
I'm well ware that they can be sycophantic, and I structure things to avoid that like asking "what do you think of this problem" and seeing the idea fall out rather than providing …
-
comment
Comment #46452975
> AI seems to have caught up to my own intelligence even in those narrow domains where I have some expertise. What is there left that AI can’t do that I would be able to verify? Th…
-
comment
Comment #46395430
Is it just me or is codex slow ? With claude code I'll ask it to read a couple of files and do x similar to existing thing y. It takes a few moments to read files and then just doe…
-
comment
Comment #46180074
What do these look like?
-
comment
Comment #46130778
> Everything it does can be done reasonable well with list comprehensions and objects that support type annotations and runtime type checking (if needed). I see this take somewhat …
-
comment
Comment #46092721
Yes and anyone who knows anything about software dev knows that the first thing you should do with an important repo is set up branch protections to disallow that, and require revi…
-
comment
Comment #46092432
It does largely avoid the issue if you configure to allow only specific environments AND you require reviews before pushing/merging to branches in that environment. https://docs.py…
-
comment
Comment #45934442
Along with a bunch of limitations that make it useless for anything but trivial use cases https://docs.claude.com/en/docs/build-with-claude/structured... I've found structured outp…
-
comment
Comment #45283964
Big missing piece - what was the impact of the degraded quality? Was it 1% worse / unnoticeable? Did it become useless? The engineering is interesting but I'd like to see it tied t…
-
comment
Comment #44411014
We operate a saas where a common step is inputting rates of widgets in $/widget, $/widget/day, $/1kwidgets, etc etc. These are incredibly tedious and error prone to enter. And usua…
-
comment
Comment #44383465
I gave it a shot just now with a fairly simple refactor. +19 lines, -9 lines, across two files. Totally ballsed it up. Defined one of the two variables it was meant to, referred to…
-
comment
Comment #43779291
Nice. Can run with `uvx --from lmnr-index --python 3.12 index run`
-
comment
Comment #43749489
Are there string prefixes for i18n stuff?
-
comment
Comment #43480483
What MCP servers do you use?
-
comment
Comment #43420736
I have found LLMs to be very good at the kind of code -> diagram task presented here. Fire up superwhisper[1] and stream-of-consciousness away about why you want the diagram, which…
-
comment
Comment #43420155
Nice btw with claude desktop you can easily hack it to auto-allow MCP, save yourself from clicking "allow" all the time. Dangerous of course if you auto-approve write actions! http…
-
comment
Comment #43419468
Yeah I get this. Often I'll prompt it like "my intern looked at this and said maybe you should x. What do you think?" Seems to help.