pull down to refresh

Nightshade: "Poison" AI models with corrupted training dataventurebeat.com/ai/meet-nightshade-the-new-tool-allowing-artists-to-poison-ai-models-with-corrupted-training-data/
10 sats \ 0 comments \ @TheWildHustle 25 Oct 2023 tech
related
Planting Undetectable Backdoors in Machine Learning Modelsarxiv.org/pdf/2204.06974
250 sats \ 4 comments \ @itsrealfake 3 Oct tech
Hundreds of MCP Servers Expose AI Models to Abuse, RCEshare.google/xaqC30NQfuObj4LqU
121 sats \ 0 comments \ @ch0k1 26 Jun news
AI Can Be Used To Develop Biological And Chemical Weaponswww.zerohedge.com/political/ai-can-be-used-develop-biological-and-chemical-weapons
175 sats \ 1 comment \ @Coinsreporter 9 Aug AI
Sycophantic | Top AI models keep saying you’re right, and that’s the problemwww.theregister.com/2025/10/05/ai_models_flatter_users_worse_confilict/
195 sats \ 3 comments \ @0xbitcoiner 6 Oct AI
When AI Learns To Liewww.forbes.com/sites/craigsmith/2025/03/16/when-ai-learns-to-lie
80 sats \ 3 comments \ @Coinsreporter 17 Mar AI
AI devs close to scraping bottom of data barrelwww.theregister.com/2025/10/03/ai_training_requires_more_data/
427 sats \ 10 comments \ @0xbitcoiner 5 Oct AI
This new data poisoning tool lets artists fight back against generative AIwww.technologyreview.com/2023/10/23/1082189/data-poisoning-artists-fight-generative-ai/
1129 sats \ 2 comments \ @kemal 25 Dec 2023 tech
AI: Accelerated Incompetencewww.slater.dev/accelerated-incompetence/
1830 sats \ 7 comments \ @co574 29 May devs
AI model collapse is not what we paid forwww.theregister.com/2025/05/27/opinion_column_ai_model_collapse/
151 sats \ 0 comments \ @k00b 28 May tech
As human generated data is used up, companies resort to "Synthetic data"www.nytimes.com/2024/04/06/technology/tech-giants-harvest-data-artificial-intelligence.html?ugrp=u&unlocked_article_code=1.i00.2gRB.J2qpf6PYyX6b&smid=url-share
2618 sats \ 7 comments \ @chaoticalHeavy 8 Apr 2024 AI
AI models collapse when trained on recursively generated data - Naturewww.nature.com/articles/s41586-024-07566-y
42 sats \ 0 comments \ @Rsync25 24 Jul 2024 alter_native
Is AI really trying to escape human control and blackmail people?arstechnica.com/information-technology/2025/08/is-ai-really-trying-to-escape-human-control-and-blackmail-people/
163 sats \ 5 comments \ @jakoyoh629 14 Aug AI
Open Source AI Spam: Further Commentary
1570 sats \ 6 comments \ @halleck 10 May 2024 devs freebie
"Maladaptive Traits": AI Systems Are Learning To Lie And Deceivewww.zerohedge.com/technology/maladaptive-traits-ai-systems-are-learning-lie-and-deceive
127 sats \ 3 comments \ @Rsync25 16 Jun 2024 alter_native
Three Horrifying Consequences Of AI That You Might Not Have Thought Aboutwww.zerohedge.com/technology/three-horrifying-consequences-ai-you-might-not-have-thought-about
30 sats \ 0 comments \ @Rothbardian_fanatic 7 Dec 2024 ideasfromtheedge
Study Says AI Becoming Masters of Deception, Teaching Itself to Lie & Manipulatethedebrief.org/shocking-new-study-says-ai-is-quickly-becoming-masters-of-deception-teaching-itself-to-lie-and-manipulate-human-users/
10 sats \ 1 comment \ @DEADBEEF 31 May 2024 tech
AI Coding Blindspotsezyang.github.io/ai-blindspots/
847 sats \ 4 comments \ @k00b 20 Mar devs
The AI Was Fed Sloppy Code. It Turned Into Something Evil. | Quanta Magazinewww.quantamagazine.org/the-ai-was-fed-sloppy-code-it-turned-into-something-evil-20250813/
110 sats \ 3 comments \ @kehiy 14 Aug AI
Design AI to fail - A question of when, not if, your system runs into its limitsfrontierai.substack.com/p/design-ai-to-fail
10 sats \ 0 comments \ @deSign_r 16 May Design
Is It EVEN Possible To Reverse Engineer AI’s Training Data?www.youtube.com/watch?v=Nie5L7Z6-qk
169 sats \ 0 comments \ @carter 21 Sep AI
Adversarial Confusion Attacks: Disrupting Multimodal LLMs - Jakub Hoscilowiczwww.researchgate.net/publication/396235412_Adversarial_Confusion_Attacks_Disrupting_Multimodal_LLMs
146 sats \ 0 comments \ @Scoresby 6 Oct AI