https://knowledged.to/tags/notes/Recent content in Notes on knowledged.toHugoen-usSat, 16 May 2026 21:38:50 +0530https://knowledged.to/notes/ml/ai-agents-in-go/Sat, 16 May 2026 15:58:30 +0000https://knowledged.to/notes/ml/ai-agents-in-go/Guide to building AI agents in Go using agent SDKs, with a minimal runnable example covering LLM integration, tools, and multi-agent workflows.https://knowledged.to/notes/ml/open-weight-models/Sun, 26 Apr 2026 15:36:37 +0000https://knowledged.to/notes/ml/open-weight-models/Explanation of open-weight models, their differences from closed and open-source models, and why they matter for local AI deployment and customization.https://knowledged.to/notes/ml/cross-entropy-in-ai/Sat, 25 Apr 2026 16:47:31 +0000https://knowledged.to/notes/ml/cross-entropy-in-ai/Explanation of cross-entropy as a loss function in AI, including intuition, formal definition, examples, and relationship to entropy and KL divergencehttps://knowledged.to/notes/ml/ai-prompts/Thu, 16 Apr 2026 22:42:26 +0530https://knowledged.to/notes/ml/ai-prompts/Overview of the different types of AI prompts including system, user, few-shot, zero-shot, chain-of-thought, meta, and retrieval-augmented promptshttps://knowledged.to/notes/ml/elastic-looped-transformers/Thu, 16 Apr 2026 22:36:40 +0530https://knowledged.to/notes/ml/elastic-looped-transformers/Overview of Elastic Looped Transformers, an adaptive compute architecture that loops a shallow transformer block multiple times to dynamically allocate compute based on input complexityhttps://knowledged.to/notes/ml/tempo-framework/Thu, 16 Apr 2026 22:15:24 +0530https://knowledged.to/notes/ml/tempo-framework/Overview of Tempo, a query-aware temporal compression framework for long-video understanding in multimodal AI, using a small VLM to filter relevant frames before passing a condensed representation to a large modelhttps://knowledged.to/notes/ml/memory-augmented-architectures/Thu, 16 Apr 2026 22:04:57 +0530https://knowledged.to/notes/ml/memory-augmented-architectures/Overview of memory-augmented neural network architectures that add dynamic external memory to models, covering NTMs, RAG, Memorizing Transformers, Titans, and practical implications for building persistent AI agentshttps://knowledged.to/notes/ml/forward-pass-and-single-pass/Thu, 16 Apr 2026 21:19:49 +0530https://knowledged.to/notes/ml/forward-pass-and-single-pass/Explanation of forward pass and single pass in LLMs, how transformer computation flows from embedding to output logits, and how speculative decoding exploits transformer parallelism to reduce large-model forward passeshttps://knowledged.to/notes/ml/speculative-decoding/Thu, 16 Apr 2026 20:54:05 +0530https://knowledged.to/notes/ml/speculative-decoding/Explanation of speculative decoding, an inference optimization that uses a fast draft model to propose tokens verified in parallel by a large model, achieving 2–3x throughput gains with identical output qualityhttps://knowledged.to/notes/ml/llm-model-weights/Mon, 13 Apr 2026 19:17:58 +0530https://knowledged.to/notes/ml/llm-model-weights/Explanation of what model weights are in LLMs, how they encode learned behaviour, why parameter count matters, and how systems like Ollama load them into memoryhttps://knowledged.to/notes/ml/gguf-models/Fri, 10 Apr 2026 09:11:52 +0530https://knowledged.to/notes/ml/gguf-models/Overview of the GGUF binary format for storing and distributing LLMs locally, including quantization levels, key characteristics, and popular runtimes like llama.cpp and Ollamahttps://knowledged.to/notes/ml/prompt-bias-in-ai/Thu, 09 Apr 2026 20:58:42 +0530https://knowledged.to/notes/ml/prompt-bias-in-ai/Explanation of prompt bias, how prompt wording and framing skew AI outputs, common forms including leading questions and assumption bias, and practical advice for writing neutral promptshttps://knowledged.to/notes/ml/primacy-bias-in-llm-style-selection/Wed, 08 Apr 2026 21:43:53 +0530https://knowledged.to/notes/ml/primacy-bias-in-llm-style-selection/Explanation of primacy bias in LLM selector prompts, how alphabetical candidate ordering caused over-selection of certain styles in BHQ, and fixes using deterministic non-lexicographic shufflinghttps://knowledged.to/notes/devops/slack-mcp-ideas/Wed, 08 Apr 2026 15:12:20 +0530https://knowledged.to/notes/devops/slack-mcp-ideas/Ideas for using Slack MCP to monitor automation opportunities and identify duplicated efforts within an organisationhttps://knowledged.to/notes/ml/elo-scoring-for-ai-models/Tue, 07 Apr 2026 22:15:56 +0530https://knowledged.to/notes/ml/elo-scoring-for-ai-models/Explanation of how ELO scoring is applied to rank AI models via human preference votes, including the math, strengths, weaknesses, and real-world use in Chatbot Arenahttps://knowledged.to/notes/ml/knowledge-distillation/Mon, 06 Apr 2026 22:43:20 +0530https://knowledged.to/notes/ml/knowledge-distillation/Overview of knowledge distillation, how student models learn from teacher model outputs, and applications including edge deployment, speculative decoding, and LLM traininghttps://knowledged.to/notes/ml/training-free-grpo/Mon, 06 Apr 2026 22:33:04 +0530https://knowledged.to/notes/ml/training-free-grpo/Overview of Training-Free GRPO, a method that improves LLM agent performance by updating model context (experience library) instead of parameters, achieving RL-like gains at a fraction of the costhttps://knowledged.to/notes/ml/attention-mechanism/Mon, 06 Apr 2026 22:18:46 +0530https://knowledged.to/notes/ml/attention-mechanism/Explanation of the attention mechanism in AI, including self-attention, cross-attention, multi-head attention, and the mathematical formulation behind Transformershttps://knowledged.to/notes/ml/transformer-architecture/Mon, 06 Apr 2026 22:15:42 +0530https://knowledged.to/notes/ml/transformer-architecture/Overview of the Transformer architecture including self-attention, multi-head attention, positional encoding, encoder-decoder structure, and key variants like BERT, GPT, and T5https://knowledged.to/notes/ml/recurrent-neural-networks/Mon, 06 Apr 2026 22:12:16 +0530https://knowledged.to/notes/ml/recurrent-neural-networks/Overview of RNNs, their memory mechanism, common variants (LSTM, GRU), use cases, and how they compare to Transformershttps://knowledged.to/notes/ml/rlhf-and-dpo/Mon, 06 Apr 2026 22:03:50 +0530https://knowledged.to/notes/ml/rlhf-and-dpo/Comparison of RLHF and DPO alignment techniques, covering their pipelines, strengths, weaknesses, and where each is used in practicehttps://knowledged.to/notes/ml/instruction-tuning/Mon, 06 Apr 2026 21:54:49 +0530https://knowledged.to/notes/ml/instruction-tuning/Overview of instruction tuning, how it works, dataset construction, and variants like RLHF, RLAIF, and DPOhttps://knowledged.to/notes/ml/perplexity-in-language-models/Mon, 06 Apr 2026 21:46:03 +0530https://knowledged.to/notes/ml/perplexity-in-language-models/Explanation of perplexity as a language model evaluation metric, including the formula, intuition, caveats, and relationship to cross-entropy losshttps://knowledged.to/notes/ml/model-quantization/Mon, 06 Apr 2026 21:39:37 +0530https://knowledged.to/notes/ml/model-quantization/Overview of model quantization techniques, precision levels, and trade-offs for reducing neural network memory and improving inference speedhttps://knowledged.to/notes/devops/gcloud-quick-reference/Mon, 06 Apr 2026 19:06:46 +0530https://knowledged.to/notes/devops/gcloud-quick-reference/Quick reference for common gcloud commands including authentication, project setup, and GKE cluster configurationhttps://knowledged.to/notes/devops/kubernetes-port-forward/Mon, 06 Apr 2026 18:59:45 +0530https://knowledged.to/notes/devops/kubernetes-port-forward/Quick reference for kubectl port-forward command syntax