@anon
sign up
@anon
sign up
pull down to refresh
A small number of samples can poison LLMs of any size
www.anthropic.com/research/small-samples-poison
280 sats
\
1 comment
\
@carter
23h
AI
related
Scientists Detect Unusual Airborne Toxin in the United States for the First Time
scitechdaily.com/scientists-detect-unusual-airborne-toxin-in-the-united-states-for-the-first-time/
50 sats
\
0 comments
\
@ch0k1
16 Jun
news
Most midi-chlorian toxicity: Matthew Krater, @Darthcoin, or Aleksandar Svetski?
22 sats
\
3 comments
\
@mallardshead
19 Feb 2023
bitcoin
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
arxiv.org/abs/2510.07192
100 sats
\
0 comments
\
@0xbitcoiner
18h
AI
Are LLMs random?
rnikhil.com/2025/04/26/llm-coin-toss-odd-even
269 sats
\
1 comment
\
@carter
30 Apr
AI
What will be the consequences of LLMs, being indistinguishable from human?
340 sats
\
13 comments
\
@Aardvark
13 Mar
AskSN
CONFIRMED: LLMs have indeed reached a point of diminishing returns
garymarcus.substack.com/p/confirmed-llms-have-indeed-reached
20 sats
\
1 comment
\
@Rsync25
10 Nov 2024
tech
More Artificial than Intelligent, it is only getting worse - Mathjis Lagerberg
mlagerberg.com/much-a-little-i-and-it-is-not-getting-better/
217 sats
\
4 comments
\
@Scoresby
15 Jul
AI
LLMs are cheap
www.snellman.net/blog/archive/2025-06-02-llms-are-cheap/
10 sats
\
0 comments
\
@hn
9 Jun
tech
LiveBench - A Challenging, Contamination-Free LLM Benchmark
livebench.ai
161 sats
\
0 comments
\
@supratic
17 Jul
AI
How Serious a Threat is LinkingLion?
201 sats
\
2 comments
\
@siggy47
31 Mar 2023
bitcoin
Mushroom Spirit on Poisons
18 sats
\
0 comments
\
@bitcoingraffiti
24 Mar
art
How do you use LLMs?
891 sats
\
8 comments
\
@gmd
21 Mar
AI
Lab leak latest evidence summary - Dr John Campbell
357 sats
\
1 comment
\
@cristaiji
15 Jun 2024
news
Get the hell out of the LLM as soon as possible
sgnt.ai/p/hell-out-of-llms/
71 sats
\
1 comment
\
@hn
1 Apr
tech
A call to toxicity
1258 sats
\
29 comments
\
@purpurato
10 Aug 2023
bitcoin
LLMs generate slop because they avoid surprises by design - Dan Fabulich
danfabulich.medium.com/llms-tell-bad-jokes-because-they-avoid-surprises-7f111aac4f96
343 sats
\
2 comments
\
@Scoresby
19 Aug
AI
Agentic Misalignment: How LLMs could be insider threats
www.anthropic.com/research/agentic-misalignment
100 sats
\
0 comments
\
@carter
8 Aug
AI
Are LLMs able to notice the “gorilla in the data”?
chiraaggohel.com/posts/llms-eda/
99 sats
\
1 comment
\
@hn
8 Feb
tech
The legacy of chemical attacks
16 sats
\
0 comments
\
@XScoins
24 Aug 2023
meta
Incredible life advice from the wise Lyn Alden on toxicity
twitter.com/LynAldenContact/status/1550252000897601538?t=6_QEOFY2gpj5OBlxPo5kZA&s=19
42 sats
\
1 comment
\
@sb
22 Jul 2022
bitcoin
Why the Pesticide Liability Protection Act Threatens our Food Supply
brookemillermd.substack.com/p/a-doctors-call-to-action-why-the
36 sats
\
0 comments
\
@Rothbardian_fanatic
6 Aug
Politics_And_Law
more