Etiqueta: fine-tuning

01 may 2026

• permanent
• rlhf
• constitutional-ai
• rlaif
• ppo
• reward-model
• alignment
• ai-safety
• fine-tuning
• sft
• anthropic
• openai
• puma-core
• research
• training
• ethics
• llm
• models
• hitl

14 abr 2026

• literature
• transformers
• hugging-face
• nlp
• fine-tuning
• quantization
• ollama
• open-weights
• mistral
• gemma
• bert
• puma-core
• book
• implementation
• python
• literature-note
• moc

13 abr 2026

• permanent
• fine-tuning
• lora
• qlora
• quantization
• gguf
• ollama
• llm
• training
• puma-core
• research
• agents
• benchmark
• local-models
• effort-estimation
• issue-triage
• architecture

07 abr 2026

• prompt
• gemini
• conceptual-model
• dsr
• puma
• academic-writing
• artefact
• benchmark
• clustering
• dataset
• few-shot
• fine-tuning
• google
• hypothesis
• keshav
• literature-review
• moc
• multi-agent
• obsidian
• planning
• project-management
• prompt-template
• reading-method
• research
• research-methodology
• slr
• sprint
• tfg
• thesis
• vault

06 abr 2026

• literature
• llm-agents
• react
• reasoning
• acting
• prompting
• puma-core
• academic-writing
• agents
• api
• architecture
• benchmark
• bibliography
• chain-of-thought
• citation
• cot
• critical-thinking
• effort-estimation
• embeddings
• few-shot
• fine-tuning
• issue-triage
• jira
• keshav
• literature-note
• llm
• moc
• multi-agent
• permanent-note
• project-management
• rag
• reading-method
• reasoning-action
• red-teaming
• research
• retrieval
• sdd
• smart-pmo
• spec-driven-development
• story-points
• triage
• vector-db

06 abr 2026

• literature
• llm-reasoning
• chain-of-thought
• self-training
• thinking
• academic-writing
• bibliography
• citation
• cot
• fine-tuning
• keshav
• literature-note
• llm
• moc
• project-management
• reading-method
• reasoning
• research
• supervised-learning
• unsupervised-learning
• zero-shot

06 abr 2026

• videos
• llm-agents
• multi-agent
• agentic-ai
• autoresearch
• karpathy
• puma
• academic-writing
• anthropic
• architecture
• autogen
• benchmark
• claude
• context-engineering
• crewai
• dev-tools
• evaluation
• fine-tuning
• ide
• langchain
• langgraph
• literature-note
• llama
• llm
• local-llm
• mas
• mcp
• meta
• metrics
• moc
• nlp
• obsidian
• opencode
• orchestration
• para
• precision-recall
• project-management
• protocol
• python
• rag
• react
• reasoning-action
• research
• retrieval
• smart-pmo
• testing
• vault
• workflow

06 abr 2026

• video
• agents
• rag
• fine-tuning
• specialisation
• academic-writing
• benchmark
• embeddings
• issue-triage
• jira
• llm
• metrics
• moc
• precision-recall
• project-management
• research
• retrieval
• swe-bench
• triage
• vector-db
• video-note

06 abr 2026

• video
• llm
• architecture
• transformer
• theory
• attention
• chain-of-thought
• cot
• few-shot
• fine-tuning
• gpt
• llama
• meta
• metrics
• mistral
• moc
• openai
• precision-recall
• project-management
• video-note

06 abr 2026

• videos
• project-management
• agile
• scrum
• pm-ai
• puma
• academic-writing
• aiops
• anthropic
• automation
• cicd
• claude
• dev-tools
• devops
• fine-tuning
• gemini
• google
• ide
• knowledge-management
• literature-note
• llm
• mcp
• metrics
• moc
• monitoring
• observability
• obsidian
• para
• pkm
• precision-recall
• protocol
• rag
• retrieval
• second-brain
• smart-pmo
• software-engineering
• sprint
• thesis
• vault
• workflow

06 abr 2026

• permanent-note
• rag
• embeddings
• vector-database
• llm
• puma
• architecture
• chain-of-thought
• cot
• critical-thinking
• dataset
• effort-estimation
• few-shot
• fine-tuning
• issue-triage
• jira
• llama
• local-llm
• memory
• meta
• metrics
• moc
• nlp
• ollama
• pipeline
• precision-recall
• project-management
• react
• reasoning-action
• red-teaming
• retrieval
• story-points
• triage
• vector-db

06 abr 2026

• bmad
• prd
• requirements
• puma
• sdd
• anthropic
• api
• architecture
• artefact
• benchmark
• bias
• carbon-footprint
• chain-of-thought
• claude
• codecarbon
• cot
• critical-thinking
• dataset
• dsr
• effect-size
• effort-estimation
• ethics
• falsifiability
• fine-tuning
• github
• gpt
• hypothesis
• ict
• issue-triage
• jira
• literature-review
• llama
• llm
• local-llm
• meta
• metrics
• mistral
• moc
• multi-agent
• non-parametric
• ollama
• openai
• pec
• planning
• popper
• precision-recall
• project-management
• python
• rag
• red-teaming
• research-methodology
• retrieval
• slr
• smart-pmo
• software-engineering
• spec-driven-development
• sprint
• statistics
• story-points
• sustainability
• tawos
• triage
• wilcoxon

06 abr 2026

• glossary
• reference
• definitions
• academic-writing
• agile
• ai-tools
• ami
• anythingllm
• api
• artefact
• backlog
• baseline
• bdd
• benchmark
• bias
• bmad
• carbon-footprint
• chain-of-thought
• code-review
• codecarbon
• contextual-anchoring
• cornell-notes
• cot
• critical-thinking
• data-formats
• dataset
• dev-tools
• drca
• dsr
• effect-size
• effort-estimation
• egi
• elicit
• embeddings
• ethics
• evaluation
• few-shot
• fine-tuning
• finer
• github
• gpt
• gtd
• human-in-the-loop
• ict
• iipr
• index
• issue-triage
• jira
• johnny-decimal
• json
• keshav
• knowledge-management
• langchain
• langgraph
• literature-review
• llama
• llm
• lm-studio
• local-llm
• memory
• meta
• metrics
• mistral
• moc
• multi-agent
• navigation
• neural-network
• non-parametric
• note-taking
• obsidian
• ollama
• one-shot
• openai
• opencode
• openspec
• orchestration
• para
• pec
• perplexity
• pipeline
• precision-recall
• prisma
• project-management
• prompt-engineering
• prompting
• puma
• python
• rag
• rcoif
• reading-method
• reasoning
• red-teaming
• research
• research-methodology
• research-tools
• rest-api
• retrieval
• sdd
• slr
• smart-pmo
• software-engineering
• spec-driven-development
• spec-kit
• sprint
• statistics
• story-points
• sustainability
• tawos
• triage
• vault
• vector-db
• wilcoxon
• workflow
• zero-shot
• zettelkasten

06 abr 2026

• glossary
• reference
• definitions
• supplement
• academic-writing
• accuracy
• agentscope
• ai-tools
• aiops
• ami
• anthropic
• api
• architecture
• auc
• autogen
• backlog
• baseline
• benchmark
• bias
• chain-of-thought
• claude
• cot
• crewai
• data-formats
• dataset
• devops
• drca
• effect-size
• effort-estimation
• egi
• embeddings
• ethics
• evaluation
• few-shot
• fine-tuning
• github
• gpt
• human-in-the-loop
• hypothesis
• ict
• iipr
• issue-triage
• jira
• json
• keshav
• langchain
• langgraph
• literature-review
• llama
• llm
• lm-studio
• local-llm
• mas
• memory
• meta
• metrics
• mistral
• mit-ai-lab
• multi-agent
• nlp
• non-parametric
• ollama
• one-shot
• openai
• orchestration
• perplexity
• pipeline
• planning
• precision-recall
• project-management
• prompting
• python
• rag
• rcoif
• react
• reading-method
• reasoning
• reasoning-action
• reinforcement-learning
• research
• research-methodology
• rest-api
• retrieval
• security
• slr
• software-engineering
• sprint
• statistics
• story-points
• supervised-learning
• swarm-intelligence
• swe-bench
• tawos
• tool-use
• transformer
• tree-of-thoughts
• triage
• validity
• vector-db
• wilcoxon
• wp316
• zero-shot

01 mar 2026

• project
• chapter
• discussion
• conclusions
• limitations
• future-work
• academic-writing
• accuracy
• api
• backlog
• benchmark
• bias
• bmad
• chain-of-thought
• code-review
• cot
• critical-thinking
• dataset
• effort-estimation
• embeddings
• ethics
• fairness
• fine-tuning
• github
• gpt
• gtd
• hypothesis
• ict
• iipr
• issue-triage
• jira
• llama
• llm
• local-llm
• meta
• metrics
• moc
• multi-agent
• navigation
• non-parametric
• openai
• pec
• precision-recall
• project-management
• project-note
• prompting
• puma
• rag
• red-teaming
• research
• research-methodology
• retrieval
• smart-pmo
• statistics
• story-points
• tawos
• triage
• validity
• vector-db
• wilcoxon

01 mar 2026

• gtd
• someday
• ideas
• future
• academic-writing
• aiops
• api
• architecture
• backlog
• benchmark
• bias
• chain-of-thought
• code-review
• cot
• crewai
• dataset
• dev-tools
• devops
• effort-estimation
• ethics
• fairness
• fine-tuning
• github
• issue-triage
• jira
• langgraph
• literature-review
• llama
• llm
• local-llm
• mas
• meta
• mistral
• multi-agent
• obsidian
• ollama
• opencode
• project-management
• projects
• pydantic
• python
• rag
• research
• research-tools
• retrieval
• sdd
• slr
• smart-pmo
• spec-driven-development
• story-points
• tawos
• triage
• vault
• zero-shot
• zotero