Viewing profile — the_duke
the_duke
HN member- Joined
- Sat, Jun 04, 2016, 9:46 AM UTC
- HN karma
- 17,627
- Public activity
- 2,816 items
- HN profile
- View on Hacker News ↗
About the_duke
No profile information was provided.
Recent public activity
-
comment
Comment #49216461
Yeah, I saw the same thing - quite annoying. It can be mitigated through the prompt.
-
comment
Comment #49178171
That's not true, pi auto-compacts when getting close to the context window limit?
-
comment
Comment #48933054
Codex CLI was open source from the start. The reason they open sourced this is because grok-build uploaded entire directories.
-
comment
Comment #48881994
No clue, I also vouched.
-
comment
Comment #48877134
I was investigating the design a little. Two big questions: A) You notably don't write a recovery log (WAL/journal) for things not yet flushed, so data can be lost. Do you have pla…
-
comment
Comment #48596963
Making something 50-2000x faster is pointless? Besides that, Rust code is actually much easier to maintain , thanks to type system guarantees.
-
comment
Comment #48574139
Does this support using S3 as the backing store? That would be very powerful for various use cases.
-
comment
Comment #48190252
In my opinion cursor actually has one of the best harnesses again at the moment.
-
comment
Comment #48185864
Of course they will. Right now they want to prevent the US labs from gaining any sort of self-reinforcing oligopoly on the space, and to let the ecosystem in China flourish. That w…
-
comment
Comment #48107725
This is often due to (privacy) extensions disabling canvas/webgl.
-
comment
Comment #48053998
In codex CLI /status works just fine during a turn. Other things don't though.
-
comment
Comment #47947862
I exclusively use thinking mode, which is slower but much more likely to double-check things with web search etc.
-
comment
Comment #47878079
Config based hooks seem to miss the mark though? The per-repo config is in `.git/config`, so that can still not be checked into the repo itself, unless I'm missing something? So no…
-
comment
Comment #47662050
That's in part because many EU countries would like to ship the Syrian refugees back to Syria.
-
comment
Comment #47442462
Any recommendations?
-
comment
Comment #47354813
You shouldn't be downvoted - LLMs could in theory be deterministic, but they currently are not, due to how models are implemented.
-
comment
Comment #47352448
I think many have adopted "spec driven development" in the way you describe. I found it works very well in once-off scenarios, but the specs often drift from the implementation. Ev…
-
comment
Comment #47352008
This doesn't make too much sense to me. * This isn't a language, it's some tooling to map specs to code and re-generate * Models aren't deterministic - every time you would try to …
-
comment
Comment #47332365
Rust has managed just fine to remain mostly backwards compatible since 1.0 , while still allowing for evolution of the language through editions. This puts much more work on the co…
-
comment
Comment #47296254
What context length and related performance are you getting out if this setup? At least 100k context without huge degradation is important for coding tasks. Most "I'm running this …
-
comment
Comment #47275578
Musk is actually a brilliant marketer. He built his companies around a "vision", used it to attract high quality talent and push that talent to give their best. For Tesla it was "e…
-
comment
Comment #47270721
Good PR moves.
- comment
-
comment
Comment #47150980
Rust has an interesting crate for this, arc-swap [1]. It's essentially just an atomic pointer that can be swapped out. [1] https://docs.rs/arc-swap/latest/arc_swap/
-
comment
Comment #47127174
Rust has a very strict type system and an ecosystem that often utilizes the type system well. Many things that would only be caught at runtime in other languages are caught at comp…