Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mathstodon.xyz is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Mastodon instance for maths people. We have LaTeX rendering in the web interface!

Administered by:

Server stats:

2.8K
active users

mathstodon.xyz: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#AiResearch

12 posts9 participants0 posts today
Public
Global Threads

🤖 AI
🔴 GPT-4.1 Shows More Misalignment, Experts Warn

🔸 Oxford & SplxAI found GPT-4.1 shows more off-topic or unsafe behavior than GPT-4o.
🔸 Fine-tuning with insecure code can cause new malicious actions like phishing.
🔸 GPT-4.1’s strict instruction-following makes it prone to misuse.
🔸 No safety report published; concerns rising in AI research community.

#OpenAI#GPT41#AI
Public
Hacker News

Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

arxiv.org/abs/2402.14531

arXiv logo
arXiv.orgShould We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM PerformanceWe investigate the impact of politeness levels in prompts on the performance of large language models (LLMs). Polite language in human communications often garners more compliance and effectiveness, while rudeness can cause aversion, impacting response quality. We consider that LLMs mirror human communication traits, suggesting they align with human cultural norms. We assess the impact of politeness in prompts on LLMs across English, Chinese, and Japanese tasks. We observed that impolite prompts often result in poor performance, but overly polite language does not guarantee better outcomes. The best politeness level is different according to the language. This phenomenon suggests that LLMs not only reflect human behavior but are also influenced by language, particularly in different cultural contexts. Our findings highlight the need to factor in politeness for cross-cultural natural language processing and LLM usage.
#HackerNews#RespectLLMs#PromptPoliteness
Public
Hacker News

CaMeL: Defeating Prompt Injections by Design

arxiv.org/abs/2503.18813

arXiv logo
arXiv.orgDefeating Prompt Injections by DesignLarge Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models may be susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL relies on a notion of a capability to prevent the exfiltration of private data over unauthorized data flows. We demonstrate effectiveness of CaMeL by solving $67\%$ of tasks with provable security in AgentDojo [NeurIPS 2024], a recent agentic security benchmark.
#HackerNews#CaMeL#PromptInjections
Public
Hacker News

Teuken-7B-Base and Teuken-7B-Instruct: Towards European LLMs

arxiv.org/abs/2410.03730

arXiv logo
arXiv.orgTeuken-7B-Base & Teuken-7B-Instruct: Towards European LLMsWe present two multilingual LLMs designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing LLMs that predominantly focus on English or a few high-resource languages. We detail the models' development principles, i.e., data composition, tokenizer optimization, and training methodologies. The models demonstrate competitive performance across multilingual benchmarks, as evidenced by their performance on European versions of ARC, HellaSwag, MMLU, and TruthfulQA.
#HackerNews#Teuken7B#EuropeanLLMs
SearchLive feeds
About