olaird25
Re:We Must Pace the Frontier
on Saturday September 12, 2026 @11:33AM (#49673376)
Vitalik Buterin: “...But currently, I see zero plans for how to deal with an ASI transition that are not naive. Perhaps humanity is stuck with a choice between naive and naive squared (or maybe even naive squared and naive cubed), so I feel inclined to cut some slack to people who are trying.”
Re:Show HN: Drift – an embedding-model upgrade should be a rotation, n...
on Wednesday June 10, 2026 @01:03PM (#48479302)
Interesting. But if you are upgrading your embedding model, wouldn't you want to re-embed to get its benefits on old entries?
Re:Show HN: RainBreak App – The AI doesn't need a break. But you do
on Tuesday June 09, 2026 @06:30PM (#48468703)
Very nice! How did you implement your rain effect?
Re:Show HN: Formally verified polygon intersection – Opus 4.8 oneshots...
on Friday June 05, 2026 @10:54AM (#48413360)
Nice. So is the js/lean interface using exact rationals?
Re:Show HN: Formally verified polygon intersection – Opus 4.8 oneshots...
on Thursday June 04, 2026 @06:58PM (#48405814)
Is the web demo compiled from the lean?
Re:Tokenization Is the Bottleneck You're Not Measuring
on Tuesday May 26, 2026 @01:31PM (#48282913)
Have you tried just using a faster tokenization library?
Github's BPE crate (https://crates.io/crates/bpe) advertises >10x speedup relative to HF, as do others.
Re:AI Killed Stack Overflow (and why that sucks)
on Tuesday May 26, 2026 @12:35PM (#48282080)
"Writing the question WAS the lesson"
Indeed!
Re:Code Mode: the better way to use MCP
on Saturday September 27, 2025 @06:27PM (#45399882)
This seems exactly right. Its pretty common to watch your agent making the same mcp tool call again and again as it works through a list. These kinds of cases are solved by letting the agent just call any of its mcp tools in a script.