Hacker News: apwheele

VerusCite's false positive rate is under 1%

apwheele — Sun, 25 Oct 2026 16:27:45 +0000

Article URL: https://veruscite.com/blog/veruscite-false-positive-rate

Comments URL: https://news.ycombinator.com/item?id=50233297

Points: 1

# Comments: 0

Hall of Hallucinated Citations with 125 papers logged

apwheele — Sun, 18 Oct 2026 13:08:27 +0000

Article URL: https://veruscite.com/hallucinations

Comments URL: https://news.ycombinator.com/item?id=50140782

Points: 2

# Comments: 1

New comment by apwheele in "DeepSeek search and fetch – $0.75 per 1000 successful requests"

apwheele — Sun, 18 Oct 2026 12:37:28 +0000

I am currently using Perplexity for https://veruscite.com/. Verify citations actually exist -- so get in a list of 100, half I can check with crossref, but the other half I need to do a web search and fetch to make sure they exist.

So I need higher rate limits to not make the tool come to a crawl. I probably will not consider DeepSeek API here (I have tried DeepSeek hosted at US providers, like Perplexity). The other search/fetch tools I try do not have great web coverage of Asian journals, but the fact DeepSeek API is not zero data retention I cannot get over.

Regulating tech companies like banks

apwheele — Thu, 15 Oct 2026 14:20:50 +0000

Article URL: https://crimede-coder.com/blogposts/2026/RegulateLikeBanks

Comments URL: https://news.ycombinator.com/item?id=50104085

Points: 3

# Comments: 1

New comment by apwheele in "Why academics should self publish textbooks"

apwheele — Wed, 14 Oct 2026 16:02:07 +0000

I know what you mean by "cannot write out of a paper bag". Agree AI won't help those folks (I honestly don't know how anyone has enough patience to help them).

My above prompt does indeed work well for me, but agree would likely not catch those example errors you list.

New comment by apwheele in "Why academics should self publish textbooks"

apwheele — Wed, 14 Oct 2026 14:41:36 +0000

I am maybe not using copy-editing the way you are (feel free to correct me what is more typical in the field). My prompt is not much different than "review the text for minor grammar and spelling errors, and list the corrections you would suggest". I accept the large majority of the suggestions.

For technical review of the content, I just send it out to other experts.

Why academics should self publish textbooks

apwheele — Wed, 14 Oct 2026 13:35:06 +0000

Article URL: https://andrewpwheeler.com/2026/10/14/why-academics-should-self-publish-textbooks/

Comments URL: https://news.ycombinator.com/item?id=50087573

Points: 2

# Comments: 6

New comment by apwheele in "Anthropic AI model submits false tip on unsolved Philly murder, police say"

apwheele — Sat, 10 Oct 2026 13:29:40 +0000

I am confused by this as well, shouldn't it be all white listed sites at the start?

VerusCite reviews now cost $1

apwheele — Mon, 05 Oct 2026 17:52:03 +0000

Article URL: https://veruscite.com/blog/veruscite-reviews-now-cost-1

Comments URL: https://news.ycombinator.com/item?id=49968078

Points: 1

# Comments: 0

New comment by apwheele in "Web Search API"

apwheele — Mon, 05 Oct 2026 17:48:49 +0000

Put in the todo list to check out. If you cut web search costs even further for flash/fast search (similar to Perplexity, which is $1 per 1000 for fast search) would make it more competitive (at least for my app!)

New comment by apwheele in "Web Search API"

apwheele — Mon, 05 Oct 2026 13:12:44 +0000

So I wish I could use Google for https://veruscite.com/, but the number of Google searches are a hard cap on the account! So yes that is fine for agentic coding, but for an app that relies on web-search is not sufficient.

I am currently using Perplexity fast search and fetch, and I am happy with that. I would try our Ceramic.ai, but I need to be able to fetch the pages as well (I do not want summaries).

New comment by apwheele in "VerusCite has its first retraction"

apwheele — Fri, 02 Oct 2026 17:24:30 +0000

If you check out https://veruscite.com/hallucinations there are much more banal examples than that article.

Part of the forensic work with this, I won't ever be able to tell the difference between "I as a human messed up" vs "LLM go brr and filled in everything". So I think editor discretion when to correct vs when to retract is fine. (I do think that PLoS One correction should have been retracted as well though.)

VerusCite has its first retraction

apwheele — Fri, 02 Oct 2026 16:59:20 +0000

Article URL: https://veruscite.com/blog/veruscite-first-retraction

Comments URL: https://news.ycombinator.com/item?id=49935821

Points: 1

# Comments: 2

Adventures in using AI to write papers

apwheele — Thu, 24 Sep 2026 15:19:23 +0000

Article URL: https://andrewpwheeler.com/2026/09/24/adventures-in-using-ai-to-write-papers/

Comments URL: https://news.ycombinator.com/item?id=49831838

Points: 1

# Comments: 0

New comment by apwheele in "Jev Can't Be Calibrated"

apwheele — Wed, 23 Sep 2026 17:04:41 +0000

While this is true, it is still possible to take the probabilities and make determinations of recall and false positives using conformal sets, https://crimede-coder.com/blogposts/2026/ConfClassification

(Or just use a model to re-calibrate the probabilities, I like the conformal approach though as those rates are what I often care about.)

You just need some labelled data to generate the "corrected" probabilities (or thresholds to meet the specified error rates).