Every sentence on this wiki can be traced to a human being saying it out loud, on a specific date, into a microphone. That is the whole premise, and it is checkable rather than promised — so instead of describing the pipeline, this page takes one real sentence from a live article and follows it all the way down to the audio.
The nominal bit count of a converter does not equal its usable resolution: a 24-bit part in a handheld power-measurement instrument returned roughly 18 effective bits at its highest sample rate and little more than 19 when slowed down.[218]
"kind": practice, "claim_text": "The bit count on a converter's part number is not the number of usable bits. A 24-bit converter in a handheld power-measurement instrument returned roughly 18 effective bits at its highest sample rate and a little over 19 when slowed down.", "quote_verbatim": "a 24 bit ADC doesn't actually give you 24 usable bits out", "speaker": "Dave Jones", "episode": 218
a 24-bit ADC doesn't actually give you 24 usable bits␣a 24 bit ADC doesn't actually give you 24 usable bits outUh, because data. I could talk about that in future shows if we'd like. And of course you're, and of course you discovered that a 24 bit ADC doesn't actually give you 24 usable bits out. Sure. Of course, uh, we've been pulling, uh, in, in our highest speed settings, maybe 18 effective, um, and, and nudging a little bit over 19, uh, when we slow down and, and pay attention a little bit more.
adcadcsanalog-to-digital-convertercustom-analog-to-digital-converterspeaker field records who said the quote, not who supplied every detail in the claim, which is why a claim is written to stand on its evidence rather than on attribution.John Davis described an aluminium smelter paying seven million dollars a month for electricity, which carried monitoring on its incoming supply because a large motor going to ground could force the shutdown of a substantial fraction of that state's grid.[385]
"kind": numbers, "claim_text": "Industrial loads reach a scale where a single site is a grid-level actor: an aluminium smelter paying seven million dollars a month for electricity had monitoring on its incoming supply because a large motor going to ground could force the shutdown of a substantial fraction of that state's grid.", "quote_verbatim": "their electricity bill per month was, uh, $7 million a month", "speaker": "John Davis", "episode": 385
their electricity bill per month was␣ $7 million a monththeir electricity bill per month was, uh, $7 million a monthBut probably your, your powers, your power supply is not going to be happy wherever the hell that is. Right. And like, yeah. Uh, more like your power plant. There was a, um, wow. Yeah. One of the companies we were talking to, they do aluminum smelting and, uh, yeah, those guys. Yeah. Yeah. They, their electricity bill per month was, uh, $7 million a month, but they, um, they had a situation. They had some special monitoring on their, their, uh, their input to the plant. But either way at the substation, if, if they went to ground and they shorted, like if one of the big, big motors went to ground, um, they could actually shut down, uh, I won't say where it is cause it'll give it away. Cause I mean, there's only like seven of these places in the U S but it would like shut down half of that state's electrical grid because they would have to kill the, yeah. I mean, it's insane. It's just, you basically start to overtax the, uh, the generators, right? Because it's probably generated with steam and the generate, you know, like, yeah, like all that stuff, you know, it's all tied back somewhere. Yeah, man.
electric-gridelectrical-gridelectricity-gridpower-gridspeaker field records who said the quote, not who supplied every detail in the claim, which is why a claim is written to stand on its evidence rather than on attribution. The speaker labels here are the raw ASR ones; the repair shown in layer 02 is what the pipeline actually uses.On Digilent's low-cost development boards, the team reverse engineered the Xilinx programming cable and integrated it onto the boards, because a seventy-nine-dollar board could not be sold alongside a three-hundred-dollar programming cable; equivalent cables of Digilent's own design followed.[302]
"kind": history, "claim_text": "Reverse engineering has been used as a deliberate market entry route: a vendor's programming cable was reverse engineered and integrated onto low-cost development boards, because a seventy-nine dollar board could not be sold alongside a three-hundred-dollar programming cable. Equivalent cables of the entrant's own design followed, and after several years of demonstrated reliability the original vendor's tools began supporting that hardware.", "quote_verbatim": "we reverse-engineered Xilinx's programming cable", "speaker": "Clint Cole", "episode": 302
we reverse engineered Xilinx's programming cablewe reverse-engineered Xilinx's programming cableOkay. Yeah, and it had – it was the first board with an onboard programming circuit. So we reverse-engineered Xilinx's programming cable. I don't know if I should say this – oh, well, too late. But we reverse-engineered theirs, stuck it on our board. Nobody said anything. So that was good because you only needed the board and a cable and nothing else. Nice. See, but that's good though too because that means that ultimately that – what they really want is to sell more parts. So what – I mean, I'm sure that's in spades, right?
reverse-engineerreverse-engineeringspeaker field records who said the quote, not who supplied every detail in the claim, which is why a claim is written to stand on its evidence rather than on attribution. The speaker labels here are the raw ASR ones; the repair shown in layer 02 is what the pipeline actually uses.What the descent shows
The pipeline runs in the opposite direction to the way you just read it. Raw transcripts are swept for concept mentions; an alias table folds surface forms together and a speaker map repairs attribution; a graph of 4,016 concepts and 12,776 edges decides what deserves an article and which passages belong to it; an extraction pass turns passages into claims pinned to verbatim quotes; a verifier byte-compares every quote; a writer builds the article from the claims alone, never seeing the transcripts; and a linter rejects the result if any paragraph is uncited or any citation fails to resolve.
The layer that matters is the byte-compare. It is the one mechanism that makes the rest of it more than a plausible-sounding machine: a quote that was paraphrased, tidied, or invented does not survive it, and an article whose claims cannot be traced does not build.
What survives each stage
What this guarantees — and what it doesn’t
Guaranteed: every claim traces to a real, verbatim, byte-checked passage in a real episode you can go listen to. Nothing is sourced from a model’s general knowledge of electronics, from the web, or from vibes. 13,225 claims across the wiki carry a quote that has passed this check, and 6,625 citations resolve to a specific episode.
Not guaranteed: that the interpretation is right. The quotes are real, but an extraction can still miss sarcasm, lose context from five minutes earlier, or generalise an anecdote into a rule. ASR garble occasionally swallows a number. Speaker attribution is repaired but imperfect — where it stays doubtful, the claim is written so it doesn’t depend on who was talking, as the first trace above shows.
That residual risk is exactly what the Report button is for: highlight any sentence on any article and file an issue in one click. “The quote is real but the claim misreads it” is the failure mode we most want reported, because it is the one the machinery cannot catch by itself.
The numbers
| Episodes transcribed | 719 |
| Words of transcript | ~11 million |
| Concept mentions in the census | 270,979 |
| Alias table entries | 90,150 |
| Concept graph | 4,016 nodes, 12,776 edges |
| Verified claims extracted | 13,225 |
| Articles live | 153 of 412 planned |
| Episode citations published | 6,625 |
Everything — transcripts, census, bundles, packets, tools, this site — is in the public repo. If you want to build a piece of it yourself, start at How to contribute.
The Amp Hour is Chris Gammell and Dave Jones, and it is theirs — this is an unaffiliated fan project built out of admiration for the show, quoting briefly and always with a link home. Go listen to the real thing.