[ 02 ] KEAMANAN
Riset
Daftar 25 artikel beserta ukuran teksnya, lalu kumpulan seluruh sumber yang dirujuk. Total kata 22162, dengan 51 sumber unik yang dirujuk di seluruh arsip.
Artikel
25 tulisanSumber
51 unik- Constitutional AI: Harmlessness from AI feedbackAnthropicdipakai 1 artikelhttps://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback
- Privacy PolicyAnthropicdipakai 1 artikelhttps://www.anthropic.com/legal/privacy
- Prompt engineering overviewAnthropicdipakai 1 artikelhttps://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview
- Tool use with ClaudeAnthropicdipakai 1 artikelhttps://docs.anthropic.com/en/docs/build-with-claude/tool-use
- Attention Is All You NeedarXivdipakai 2 artikelhttps://arxiv.org/abs/1706.03762
- Constitutional AI: Harmlessness from AI FeedbackarXivdipakai 2 artikelhttps://arxiv.org/abs/2212.08073
- GPT-4 Technical ReportarXivdipakai 3 artikelhttps://arxiv.org/abs/2303.08774
- Language Models are Few-Shot LearnersarXivdipakai 4 artikelhttps://arxiv.org/abs/2005.14165
- LoRA: Low-Rank Adaptation of Large Language ModelsarXivdipakai 1 artikelhttps://arxiv.org/abs/2106.09685
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksarXivdipakai 1 artikelhttps://arxiv.org/abs/2005.11401
- RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI FeedbackarXivdipakai 1 artikelhttps://arxiv.org/abs/2309.00267
- Scaling Laws for Neural Language ModelsarXivdipakai 2 artikelhttps://arxiv.org/abs/2001.08361
- Survey of Hallucination in Natural Language GenerationarXivdipakai 1 artikelhttps://arxiv.org/abs/2202.03629
- Training Compute-Optimal Large Language ModelsarXivdipakai 1 artikelhttps://arxiv.org/abs/2203.15556
- Training language models to follow instructions with human feedbackarXivdipakai 4 artikelhttps://arxiv.org/abs/2203.02155
- llama.cppGitHubdipakai 1 artikelhttps://github.com/ggerganov/llama.cpp
- EmbeddingsGoogle AI for Developersdipakai 2 artikelhttps://ai.google.dev/gemini-api/docs/embeddings
- Function calling with the Gemini APIGoogle AI for Developersdipakai 1 artikelhttps://ai.google.dev/gemini-api/docs/function-calling
- Gemini Developer API pricingGoogle AI for Developersdipakai 1 artikelhttps://ai.google.dev/pricing
- Prompting strategiesGoogle AI for Developersdipakai 3 artikelhttps://ai.google.dev/gemini-api/docs/prompting-strategies
- Structured outputsGoogle AI for Developersdipakai 1 artikelhttps://ai.google.dev/gemini-api/docs/structured-output
- Understand and count tokensGoogle AI for Developersdipakai 3 artikelhttps://ai.google.dev/gemini-api/docs/tokens
- Data Processing TermsGoogle Clouddipakai 1 artikelhttps://cloud.google.com/terms/data-processing-addendum
- GGUFHugging Facedipakai 1 artikelhttps://huggingface.co/docs/transformers/quantization/gguf
- PEFTHugging Facedipakai 2 artikelhttps://huggingface.co/docs/peft/index
- QuantizationHugging Facedipakai 2 artikelhttps://huggingface.co/docs/transformers/main/en/quantization
- Text generationHugging Facedipakai 2 artikelhttps://huggingface.co/docs/transformers/main/en/llm_tutorial
- Tokenization algorithmsHugging Facedipakai 1 artikelhttps://huggingface.co/docs/transformers/tokenizer_summary
- EmbeddingsOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/embeddings
- EvalsOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/evals
- Function callingOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/function-calling
- PricingOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/pricing
- Production best practicesOpenAIdipakai 2 artikelhttps://platform.openai.com/docs/guides/production-best-practices
- Prompt engineeringOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/prompt-engineering
- Structured outputsOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/structured-outputs
- Text generationOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/text-generation
- Your dataOpenAIdipakai 1 artikelhttps://platform.openai.com/docs/guides/your-data
- LLM01:2025 Prompt InjectionOWASPdipakai 1 artikelhttps://genai.owasp.org/llmrisk/llm01-prompt-injection/
- OWASP Top 10 for Large Language Model ApplicationsOWASPdipakai 1 artikelhttps://genai.owasp.org/llm-top-10/
- Five-Stage Pipeline of Large Language ModelsRahulTechX (X)dipakai 1 artikelhttps://x.com/RahulTechX/status/2073977106447634474
- Context windowWikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Context_window
- Few-shot learningWikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Few-shot_learning
- Fine-tuning (deep learning)Wikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Fine-tuning_(deep_learning)
- Hallucination (artificial intelligence)Wikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Hallucination_(artificial_intelligence)
- Large language modelWikipediadipakai 4 artikelhttps://en.wikipedia.org/wiki/Large_language_model
- Prompt injectionWikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Prompt_injection
- Reinforcement learningWikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Reinforcement_learning
- Reinforcement learning from human feedbackWikipediadipakai 2 artikelhttps://en.wikipedia.org/wiki/Reinforcement_learning_from_human_feedback
- Retrieval-augmented generationWikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Retrieval-augmented_generation
- Tokenization (lexical analysis)Wikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Tokenization_(lexical_analysis)
- Word embeddingWikipediadipakai 1 artikelhttps://en.wikipedia.org/wiki/Word_embedding