Hacker News: long

The coming industrialisation of exploit generation with LLMs

long — Mon, 19 Jan 2026 07:57:04 +0000

Article URL: https://sean.heelan.io/2026/01/18/on-the-coming-industrialisation-of-exploit-generation-with-llms/

Comments URL: https://news.ycombinator.com/item?id=46676081

Points: 265

# Comments: 170

New comment by long in "Can GPT-3 AI write comedy?"

long — Sun, 13 Feb 2022 04:29:33 +0000

Hi, I work on the instruct models. Are you able to share details about the particular task you're doing and the prompts you've tried? (email: @openai.com )

New comment by long in "Plotnine: Grammar of Graphics for Python (2019)"

long — Fri, 29 Jan 2021 02:01:55 +0000

In general, the code philosophy behind ggplot2 and related tools (the so-called "tidyverse" in R) embraces functional programming, in particular doing computation by pure composition of smaller computations.

Using the "+" operator to denote composing parts of visualizations is not the greatest syntax but I think we're basically stuck with it for a bit due to historical baggage. See this note from the creator of ggplot, Hadley Wickham: https://community.rstudio.com/t/why-cant-ggplot2-use/4372/7

New comment by long in "Tether price manipulation"

long — Fri, 08 Jan 2021 22:28:51 +0000

I think the abstract does effectively say that: "these patterns are most consistent with the supply‐based hypothesis of unbacked digital money inflating cryptocurrency prices." And this point is made more forcefully in the paper.

FWIW, I don't have a strong opinion on the evidence presented in the paper -- the analyses seem sensible, but this isn't my field of expertise, so I'd be hard pressed to point out, for example, what alternative analyses they could / should have done.

Also, it's not even obvious to me that unbacked Tether causing the BTC price rallies is necessarily a reason to pull out; markets are weird.

New comment by long in "Tether price manipulation"

long — Fri, 08 Jan 2021 18:49:13 +0000

Here's an econ paper that studies that question: https://www.researchgate.net/publication/342185292_Is_Bitcoi...

New comment by long in "Ketamine: From Party Drug to Prescription Medicine"

long — Tue, 19 Mar 2019 04:32:51 +0000

Interesting.

GP seems to say that it worked wonders for them, so I'm still interested in trying it.

New comment by long in "Ketamine: From Party Drug to Prescription Medicine"

long — Tue, 19 Mar 2019 02:30:34 +0000

I've got some nerve issues and would be interested in trying this -- how did you get a hold of the cream?

New comment by long in "Why does deep and cheap learning work so well?"

long — Sat, 12 May 2018 06:05:00 +0000

I think you will like this paper then: https://arxiv.org/abs/1711.09576

New comment by long in "Giant coconut crabs feed on birds (2017)"

long — Sun, 15 Apr 2018 22:52:09 +0000

Are they tasty?

New comment by long in "Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning"

long — Sat, 18 Nov 2017 01:56:13 +0000

Thanks -- this series is excellent!

New comment by long in "Regex Puzzle"

long — Fri, 07 Jul 2017 20:49:47 +0000

So I do AI research on something pretty related to the guessing game -- I'll shoot you an email.

New comment by long in "Regex Puzzle"

long — Fri, 07 Jul 2017 19:43:15 +0000

There's a conference on grammar induction called ICGI; might wanna browse through the proceedings to see if there's anything closer.

New comment by long in "Regex Puzzle"

long — Thu, 06 Jul 2017 22:23:28 +0000

In computer science academia, this kind of game is called grammar induction (of which inferring regular expressions is a special case).

A classic algorithm for inferring regular expressions was given by Angluin: https://people.eecs.berkeley.edu/~dawnsong/teaching/s10/pape...

(This isn't quite the same setup as you're thinking of but there are a ton of variations on the basic idea)

New comment by long in "Michael K. Williams Is More Than Omar from ‘The Wire’"

long — Mon, 03 Jul 2017 07:16:32 +0000

I tried getting into Treme but couldn't hack it. Maybe I'll give it another try, though -- what was the appeal of it for you?

New comment by long in "Cooking Lessons"

long — Mon, 10 Apr 2017 03:06:38 +0000

It's not an entirely fair comparison -- the Locol burgers are a bit bigger than McDonalds (maybe something like 3 McDonalds = 2 Locol)

New comment by long in "Cooking Lessons"

long — Mon, 10 Apr 2017 03:05:04 +0000

I've eaten at the Oakland location. It's actually pretty tasty.

New comment by long in "Ask HN: What addition or change would improve your quality of life?"

long — Wed, 22 Feb 2017 22:32:11 +0000

Have you spoken to your neighbor about this?

New comment by long in "Probabilistic Models of Cognition"

long — Fri, 03 Feb 2017 00:50:28 +0000

A non-exhaustive list:

1. Pedagogically, the lispy syntax was a big stumbling block for beginners. Probabilistic programming is hard enough as it is; prefix notation and parens only added difficulties (and these difficulties were unrelated to the conceptual material).

2. webchurch compiled to Javascript anyway, so it was nice to be closer to the target language.

3. Lisp can be a bit awkward for certain contemporary programming idioms (e.g., accessing object properties).

New comment by long in "Probabilistic Models of Cognition"

long — Thu, 02 Feb 2017 18:32:32 +0000

Both. (source: I've worked on both languages and versions of the book).

But give webppl a shot -- it's a good language!

New comment by long in "Probabilistic Models of Cognition"

long — Thu, 02 Feb 2017 16:38:49 +0000

Indeed. And there is now a webppl version of the probmods textbook: http://probmods.org/v2