LLM News and Articles
Wednesday, 2024-08-07 | ||||
21:12 | Uma Arquitetura de Agentes baseada em Grafos para a Resolução de Tarefas Complexas com LLMs https://mnaweb.medium.com/uma-arquitetura-de-agentes-baseada-em-grafos-para-a-resolu%C3%A7%C3%A3o-de-tarefas-complexas-com-llms-0f5ba8783ae8 | |||
20:27 | Giving Generative AI Access to Real-Time Knowledge with the Perplexity API https://medium.com/@the.nick.miller/giving-generative-ai-access-to-real-time-knowledge-with-the-perplexity-api-55e874da3455 | |||
20:15 | Andrej Karpathy on X: RLHF is just barely RL https://twitter.com/karpathy/status/1821277264996352246 | |||
19:45 | Can a Large Language Model Recognize Itself? https://medium.com/@joel5638/can-a-large-language-model-recognize-itself-ef2e9d82cdf8 | |||
19:32 | Mistral Agents https://mistral.ai/news/build-tweak-repeat/ | |||
19:19 | Summarise New York Times news using Gemini. https://medium.com/@niltonjuniorphd/summarise-new-york-times-news-using-gemini-9761e7dbdfbb | |||
19:10 | Medical-Specific Language Model: PMC-LLaMA https://ai.gopubby.com/medical-specific-language-model-pmc-llama-d07fed1f1061 | |||
19:06 | So you want to Run the LLM model on your pc/mac. https://medium.com/@5.vivek.verma/so-you-want-to-run-the-llm-model-on-your-pc-mac-8ef11c40bccb | |||
19:01 | PromptPoet: Revolutionizing LLM Prompt Design at Character.ai https://github.com/character-ai/prompt-poet | |||
18:50 | OWASP Top Ten Large Language Model Vulnerabilities, Part 2 https://modelsandcycles.com/owasp-top-ten-large-language-model-vulnerabilities-part-2-832e90f2b924 | |||
18:46 | Mistral – Alpha Release of Agents https://mistral.ai/fr/news/build-tweak-repeat/ | |||
18:17 | Think Like a Human, Search Like a Pro: The MindSearch Revolution https://medium.com/@aarush-raj/think-like-a-human-search-like-a-pro-the-mindsearch-revolution-d5dff3a741df | |||
18:07 | Off Goes The CA https://blog.worqhat.com/off-goes-the-ca-d2ec7fc2bc82 | |||
17:59 | Customizing PaliGemma: A Guide to Fine Tuning for Targeted Applications https://medium.com/@danushidk507/customizing-paligemma-a-guide-to-fine-tuning-for-targeted-applications-636a522536cc | |||
17:56 | LangChain: Building a Custom Shell/Bash Tool Agent for Windows OS https://medium.com/@harshharsha360/langchain-building-a-custom-shell-bash-tool-agent-for-windows-os-8392b15d5de1 | |||
17:54 | Language model can listen while speaking https://huggingface.co/papers/2408.02622 | |||
17:48 | From Zero to Hero (LLMs Edition): Episode 4. Building a Chatbot with LangChain https://iamdgarcia.medium.com/from-zero-to-hero-llms-edition-episode-4-building-a-chatbot-with-langchain-424dbf365602 | |||
17:27 | How to Choose a Suitable LLM for a Business Use Case https://medium.com/@uday.sfdc1991/how-to-choose-a-suitable-llm-for-a-business-use-case-ab27cb7c021d | |||
17:22 | Sam Altman teases "Project Strawberry" (formerly Q*) https://twitter.com/sama/status/1821207141635780938 | |||
17:11 | OpenAI's Talent Retention Woes https://techcrunch.com/2024/08/07/this-week-in-ai-openais-talent-retention-woes/ | |||
17:01 | Open-Sourcing LLM App Starter Templates https://inductor.ai/blog/open-sourcing-llm-app-starter-templates | |||
16:38 | Automating Internal Writing Processes with Generative AI https://medium.com/pressw/automating-internal-writing-processes-with-generative-ai-84ed5752ba9e | |||
16:31 | Introducing Structured Outputs and ModelBox’s Support for GPT-4o-2024–08–06 inference https://medium.com/@modelbox/introducing-structured-outputs-and-modelboxs-support-for-gpt-4o-2024-08-06-inference-bd23673a19e1 | |||
16:26 | WTF Is AGI and Why is it Taking Over AI https://medium.com/@topbosstalk/wtf-is-agi-and-why-is-it-taking-over-ai-5fabf832914d | |||
16:25 | Retrieval-Augmented Generation (RAG) with LangChain and FAISS https://medium.com/@alexrodriguesj/retrieval-augmented-generation-rag-with-langchain-and-faiss-a3997f95b551 | |||
16:16 | LangGraph v0.2: Increased customization with new checkpointer libraries https://blog.langchain.dev/langgraph-v0-2/ | |||
15:49 | Agentic Prompting for LLMs: The Hype It Deserves https://medium.com/pressw/agentic-prompting-for-llms-the-hype-it-deserves-5200316c0797 | |||
15:44 | LLMs Have Ushered in a New Era of the Software Development Lifecycle (SDLC) https://medium.com/langtrace/llms-have-ushered-in-a-new-era-of-the-software-development-lifecycle-sdlc-f0fefd2aafe0 | |||
15:26 | Eliminate RAG Hallucinations with a Single API https://medium.com/@michaelwood33311/eliminate-rag-hallucinations-with-a-single-api-1d58e9deb86a | |||
15:21 | Creating a Natural Language UI like Jarvis in Iron Man: How Gen AI and LLMs Can Help https://medium.com/@shashwatbhatt190897/creating-a-natural-language-ui-like-jarvis-in-iron-man-how-gen-ai-and-llms-can-help-6850e657ff93 | |||
15:14 | Enhancing LLMs Intelligence with Advanced Knowledge Graphs using GraphRAG https://medium.com/@madzarmaksim/understanding-graphrag-enhancing-llm-capabilities-with-knowledge-graphs-2d7420bd328c | |||
14:44 | How to Use Structured Outputs with GPT-4o-2024–08–06 https://towards-agi.medium.com/how-to-use-structured-outputs-with-gpt-4o-2024-08-06-37be4a447c6f | |||
14:36 | Chain-of-Thought — All the Language Models are Just Extremely Intelligent Toddlers https://medium.com/@purusharth.19.malik/chain-of-thought-all-the-language-models-are-just-extremely-intelligent-toddlers-7f1d40bdeb8e | |||
14:29 | How to query relational databases with connected tables using a large language model https://medium.com/@jaimonjk/how-to-query-relational-databases-with-connected-tables-using-a-large-language-model-1a8aa06f40e6 | |||
14:24 | Improving Performance Time for LLMs in Windows https://medium.com/automate-everything/improving-performance-time-for-llms-in-windows-df169582ddbc | |||
14:16 | Large Language Models, Transformer Architecture, and Text Generation https://olehch.medium.com/large-language-models-transformer-architecture-text-generation-0f1a81f44873 | |||
14:12 | Film discovery — a simple RAG example https://medium.com/@uri.meirav/film-discovery-a-simple-rag-example-916a93e1888d | |||
14:10 | ChatGPT Alternatives — Exploring Free, Open-Source and Affordable AI Models https://medium.com/@linuxandbeyond/chatgpt-alternatives-exploring-free-open-source-and-affordable-ai-models-aabdd7d85b26 | |||
14:01 | Lean, Mean, Green Machines: Optimizing AI for Energy Efficiency https://medium.com/@sales_96204/lean-mean-green-machines-optimizing-ai-for-energy-efficiency-9aa75a2af04a | |||
13:49 | Il prompt engineering:
la chiave per dialogare efficacemente con l’AI https://medium.com/@gboccardo/il-prompt-engineering-la-chiave-per-dialogare-efficacemente-con-lai-2a950f90f345 | |||
13:43 | Mistral NeMo vs Llama 3.1 8B: A Comparative Analysis https://www.marktechpost.com/2024/08/07/mistral-nemo-vs-llama-3-1-8b-a-comparative-analysis/ | |||
13:37 | Develop and Deploy a Serverless RAG Solution with Amazon Bedrock agents, Knowledge Base and… https://medium.com/@miramnair/develop-and-deploy-a-serverless-rag-solution-with-amazon-bedrock-agents-knowledge-base-and-098c66f3b290 | |||
12:54 | Simple RAG with LlamaIndex, Qdrant & GPT-4o Mini https://ai.gopubby.com/simple-rag-with-llamaindex-qdrant-gpt-4o-mini-a227c343cbec | |||
12:25 | Introducing Calorie GPT: Track your Calories using LLMs — Part 1 https://medium.com/@vivekg342/introducing-calorie-gpt-track-your-calories-using-llms-part-1-4b1a854b0b28 | |||
12:07 | 6 Lessons From Llama 3 https://medium.com/@jonnyndavis/6-lessons-from-llama-3-a96d239be4fb | |||
12:03 | 10 Intersections of AI and Web Development https://alexasteinbruck.medium.com/10-intersections-of-ai-and-web-development-beb64b52848c | |||
11:39 | Text to imaging in a state of FLUX? https://ai.gopubby.com/text-to-imaging-in-a-state-of-flux-9bb3b10a1c06 | |||
11:32 | How to Automate AI to Post Facebook Posts: Developing Guide https://medium.com/@marketing_novita.ai/how-to-automate-ai-to-post-facebook-posts-developing-guide-e50f35141d69 | |||
11:32 | VERSES’ Latest Research Advances Beyond GenAI With RGM Conceptual Modeling for Faster, Cheaper AI https://medium.com/@deniseholt1/verses-latest-research-advances-beyond-genai-with-rgm-conceptual-modeling-for-faster-cheaper-ai-cd38abde04c3 | |||
11:10 | How to Maximize Business Intelligence with Large Language Models https://medium.com/@ezinsightsai/how-to-maximize-business-intelligence-with-large-language-models-63337341b281 | |||
10:16 | Revolutionizing Workflows: How LLM Agents Streamline Repetitive Tasks with Security and Efficiency https://towardsdev.com/revolutionizing-workflows-how-llm-agents-streamline-repetitive-tasks-with-security-and-efficiency-47c169463b13 | |||
09:50 | Fine-tuning or RAG ? What’s your first move in LLM optimization? https://akhinoz.medium.com/fine-tuning-or-rag-whats-your-first-move-in-llm-optimization-0c3d6b0a5e91 | |||
09:47 | Stop Wasting LLM Tokens https://towardsdatascience.com/stop-wasting-llm-tokens-a5b581fb3e6e | |||
09:41 | Create a Synthetic Dataset Using Llama 3.1 405B for Instruction Fine-Tuning https://towardsdatascience.com/create-a-synthetic-dataset-using-llama-3-1-405b-for-instruction-fine-tuning-9afc22fb6eef | |||
09:32 | Develop Forever Companion AI: Your Virtual Support https://medium.com/@marketing_novita.ai/develop-forever-companion-ai-your-virtual-support-31f198f583c6 | |||
09:29 | Not Waving But Mass-Producing https://williamessex.medium.com/not-waving-but-mass-producing-82644d3f2a3a | |||
08:54 | Develop and Deploy a Serverless RAG Solution with Amazon Bedrock agents, Knowledge Base and… https://medium.com/@miramnair/develop-and-deploy-a-serverless-rag-solution-with-amazon-bedrock-agents-knowledge-base-and-ef8a1818bc1e | |||
07:46 | Exploring Retrieval-Augmented Generation (RAG): Understanding, Evaluating, and Applying the Hybrid… https://blog.nonstopio.com/exploring-retrieval-augmented-generation-rag-understanding-evaluating-and-applying-the-hybrid-bdca9f99f6a1 | |||
07:36 | BeyondLLM 0.2.2 Release: Evaluate Langchain RAG pipeline, Memory and Weaviate support https://medium.aiplanet.com/beyondllm-0-2-2-release-evaluate-langchain-rag-pipeline-memory-and-weaviate-support-a33207b38d61 | |||
07:19 | Building RAG App Using Open-Source Cloud-Hosted LLMs with MyScaleDB and BentoML https://medium.com/@myscale/building-rag-app-using-open-source-cloud-hosted-llms-with-myscaledb-and-bentoml-2d61b4c7baf6 | |||
07:12 | Engaging Citizens Like Never Before with AI Magic! https://dirk-schmidt.medium.com/engaging-citizens-like-never-before-with-ai-magic-36e95fdb296e | |||
06:31 | The State of Customer Service in 2024: Key Points to Remember for a Generative AI Future https://medium.com/@social_65128/the-state-of-customer-service-in-2024-key-points-to-remember-for-a-generative-ai-future-b1d77ff22446 | |||
05:37 | Optimizing LLM Apps: Practical Prompt Engineering Tips https://medium.com/@analyticsinsightsubmissions/optimizing-llm-apps-practical-prompt-engineering-tips-a4f186bcf5ee | |||
05:35 | Principles of Prompt Engineering https://medium.com/@sudhirgiri/principles-of-prompt-engineering-dce12a6268c7 | |||
04:54 | Meta presents Self-Taught Evaluators: A New AI Approach that Aims to Improve Evaluators without Human Annotations and Outperforms Commonly Used LLM Judges Such as GPT-4 https://www.marktechpost.com/2024/08/06/meta-presents-self-taught-evaluators-a-new-ai-approach-that-aims-to-improve-evaluators-without-human-annotations-and-outperforms-commonly-used-llm-judges-such-as-gpt-4/ | |||
04:37 | LLM evaluation metrics — BLEU, ROGUE and METEOR explained https://avinashselvam.medium.com/llm-evaluation-metrics-bleu-rogue-and-meteor-explained-a5d2b129e87f | |||
03:57 | OpenAI’s Talent Exodus: A Sign of Shifting Priorities in AI Development https://actbrilliant.medium.com/openais-talent-exodus-a-sign-of-shifting-priorities-in-ai-development-a12033b3b7c9 | |||
03:57 | OpenAI’s Talent Exodus: A Sign of Shifting Priorities in AI Development https://digitizingpolaris.com/openais-talent-exodus-a-sign-of-shifting-priorities-in-ai-development-a12033b3b7c9 | |||
03:19 | Introducing PlugLLM: Simplify Your LLM Integration with a Unified API https://medium.com/@ryansaleh/introducing-plugllm-simplify-your-llm-integration-with-a-unified-api-259ed1c48524 | |||
03:05 | Self-Taught Evaluators: improving LLM-as-Judge evaluators without human annotations https://medium.com/@techsachin/self-taught-evaluators-improving-llm-as-judge-evaluators-without-human-annotations-71e6a73ce8c2 | |||
01:54 | OpenAI: Structured Outputs in the API https://simonwillison.net/2024/Aug/6/openai-structured-outputs/ | |||
01:50 | Pudgy Penguins Search & Discovery AI Chatbot now Live https://ai-network.medium.com/pudgy-penguins-search-discovery-ai-chatbot-now-live-c2d17688e4d8 | |||
01:49 | OpenAI has released the No. 1 feature developers have been desperate for https://venturebeat.com/ai/openai-has-finally-released-the-no-1-feature-developers-have-been-desperate-for/ | |||
01:32 | QLoRA: Revolutionizing Machine Learning with Quantized Efficiency https://medium.com/@kadamsay06/qlora-revolutionizing-machine-learning-with-quantized-efficiency-060d918b2fb6 | |||
00:36 | Iterative RAG Explained: Methods and Practical Considerations https://medium.com/@mehrdad-/iterative-rag-explained-methods-and-practical-considerations-fbf194fae991 | |||
Tuesday, 2024-08-06 | ||||
23:31 | Llama 3: Meta AI’s Multilingual and Multimodal Marvel https://medium.com/syncedreview/llama-3-meta-ais-multilingual-and-multimodal-marvel-beb2b0a864b8 | |||
22:50 | Zero-shot ECG classification using multimodal learning and test-time CKEPE https://medium.com/thedeephub/zero-shot-ecg-classification-using-multimodal-learning-and-test-time-ckepe-85f128281685 | |||
22:34 | When LLM agents can do a task, they can often do so at a fraction of human cost https://metr.org/blog/2024-08-06-update-on-evaluations/ | |||
22:25 | The Llama 3 Herd of Models https://medium.com/@EleventhHourEnthusiast/the-llama-3-herd-of-models-2f62252ce1c8 | |||
22:22 | Local RAG with Llama3-instruct (Ollama) https://levelup.gitconnected.com/local-rag-with-llama3-instruct-ollama-305a7eb749cb | |||
22:13 | Advanced Retrieval Techniques in LangChain to improve the efficiency of RAG systems https://medium.com/@abhiragkulkarni12/advanced-retrieval-techniques-in-langchain-to-improve-the-efficiency-of-rag-systems-32b88d78383d | |||
21:47 | Anthropic Embeddings https://docs.anthropic.com/en/docs/build-with-claude/embeddings | |||
21:45 | The Future of Human-Computer Interaction. 2024 and beyond!! https://medium.com/@ozziefeerman/the-future-of-human-computer-interaction-2024-and-beyond-b680c3d24ff7 | |||
21:42 | Key differences between prompt injection and jailbreaking https://kenhuangus.medium.com/key-differences-between-prompt-injection-and-jailbreaking-d397cffbe812 | |||
21:27 | Monitoring and Evaluation of LLM Systems https://njokuuchechi.medium.com/monitoring-and-evaluation-of-llm-systems-ae3e28b8ac0d | |||
21:18 | PyBench: Evaluating LLM Agent on various real-world coding tasks https://arxiv.org/abs/2407.16732 | |||
21:16 | Implementation and Evaluation of RAG using Langchain and RAGAS https://medium.com/@pdashok2875/implementation-and-evaluation-of-rag-using-langchain-and-ragas-d29c6ffc5442 | |||
21:06 | Symbolic Knowledge Distillation of Large Language Models https://medium.com/@lotussavy/symbolic-knowledge-distillation-of-large-language-models-ce01a221b1f1 | |||
20:56 | Knowledge Distillation and its types https://medium.com/@lotussavy/knowledge-distillation-and-its-types-26ee83a7d14c | |||
20:44 | MILESTONES IN KNOWLEDGE DISTILLATION AND LARGE LANGUAGE MODELS https://medium.com/@lotussavy/milestones-in-knowledge-distillation-and-large-language-models-260e7ac5a789 | |||
20:33 | Understanding LangChain-Part 2 https://medium.com/@swethag04/understanding-langchain-part-2-55587fb3beff | |||
20:12 | Exploring Google’s New Gemini 1.5 Pro Experimental 0801: The Most Powerful Model to Date https://medium.com/around-the-prompt/exploring-googles-new-gemini-1-5-pro-experimental-0801-the-most-powerful-model-to-date-b744397f581c | |||
19:47 | E²-LLM: Training long context LL https://medium.com/@JamesStakelum/e%C2%B2-llm-training-long-context-ll-d714c01fde9c | |||
19:35 | A formula to pick the most cost-effective model https://medium.com/@dschauer12/a-formula-to-pick-the-most-cost-effective-model-db20ff51afe6 | |||
18:31 | Add SALT to Your AI Prompts https://will-s-curran.medium.com/add-salt-to-your-ai-prompts-453564218670 | |||
18:28 | AlphaProof: When AI Crashed the Math Party https://medium.com/@cognidownunder/alphaproof-when-ai-crashed-the-math-party-cbe2c3cad562 | |||
18:19 | How to Use RouteAgent: A Guide to Intelligent AI Task Routing https://blog.stackademic.com/how-to-use-routeagent-a-guide-to-intelligent-ai-task-routing-33be8b6ec9f9 | |||
18:15 | Building Intelligent Agents from Scratch: A Journey into LLM-Powered Autonomy https://pub.towardsai.net/building-intelligent-agents-from-scratch-a-journey-into-llm-powered-autonomy-e998bb9e34ae | |||
18:15 | Comparing Chroma and FAISS involves examining their features, use cases, and performance. https://medium.com/@jh.baek.sd/comparing-chroma-and-faiss-involves-examining-their-features-use-cases-and-performance-f54997632cd6 | |||
17:30 | Beat GPT-4o at Python by searching with 100 dumb LLaMAs https://modal.com/blog/llama-human-eval |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803