Nathaniel Whittemore

speaker
51,978 appearances 203 recordings 3 series first heard Oct 2025 last heard 2d ago

Nathaniel Whittemore’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months
31 · Jun OctJan 26AprJulnow

Recordings per month over the last 12 months — 203 in all, peaking in Jun 2026 with 31.

Appearances

newest first · ▶ plays the moment
Does it address the export problem? podcast-host
Does it promise something unsupported by the information provided? podcast-host
And part of what people are excited about opening up with this new approach is that cheap judgment makes frequent checking more practical. podcast-host
If a check adds a noticeable delay or expense, a team may run it only on selected cases or at the end of a task. podcast-host
If it becomes sufficiently fast and inexpensive, it could run on every incoming request after each draft revision across many candidate documents before an agent takes a consequential step. podcast-host
Back in Mike Taylor's article from Every, he gave Jeff the text from all 27 of his articles, alongside 10 deliberately AI-styled counterpoints, then asked the same 21 questions concurrently across all articles to check for AI tells. podcast-host
Basically, the check that he was doing with Jev was: does this essay do specific things that indicate to people that it is AI composed? podcast-host
Things like, does the text repeat an idea without adding evidence? podcast-host
Does it podcast-host
Force a symmetrical both sides argument, does it overexplain a straightforward point? podcast-host
In less than 0.7 seconds, Mike said, Jeff quote unquote read all 37 documents and answered all 21 questions for each, returning 777 judgments for an estimated quarter of a cent. podcast-host
As he points out, that's fast and cheap enough to AI check everything everyone at your company has ever written and get the results back in an instant. podcast-host
A comparison that Mike makes. podcast-host
Is a code linter for knowledge work. podcast-host
He writes, In software development, a code linter is a tool that analyzes your work and almost instantly flags syntax errors, catches bugs, spots bad patterns, and enforces stylistic consistency. podcast-host
TypeSafe's model is so fast at turning fuzzy tasks into clear structured answers that it could act as a kind of code linter for knowledge work. podcast-host
Give Codex or Claude access to JEV and a list of questions, and it can quickly check its own work for problems you've told it to avoid. podcast-host
Peringrat says, Most software is ultimately a giant tree of if this do that, if this root here, if this escalate, if this reject, if this, ask a human. podcast-host
Jev is basically asking, what if those if statements could understand messy human context? podcast-host
That's a much more interesting framing than another AI model. podcast-host
Showing 2721–2740 of 51,978 · page 137 of 2599 ← Previous Next →