WFGY/ProblemMap/GlobalFixMap/LLM_Providers
2025-09-05 11:02:41 +08:00
..
checklists Create .gitkeep 2025-09-05 11:00:45 +08:00
eval Create .gitkeep 2025-09-05 11:01:29 +08:00
mvp_demo Create .gitkeep 2025-09-05 11:01:50 +08:00
ops Create .gitkeep 2025-09-05 11:02:04 +08:00
patterns Create .gitkeep 2025-09-05 11:02:17 +08:00
playbooks Create .gitkeep 2025-09-05 11:02:30 +08:00
tools Create .gitkeep 2025-09-05 11:02:41 +08:00
anthropic.md Update anthropic.md 2025-09-05 10:58:18 +08:00
anthropic_claude.md Update anthropic_claude.md 2025-09-05 10:58:24 +08:00
aws_bedrock.md Update aws_bedrock.md 2025-09-05 10:58:31 +08:00
azure_openai.md Update azure_openai.md 2025-09-05 10:58:38 +08:00
cohere.md Update cohere.md 2025-09-05 10:58:44 +08:00
deepseek.md Update deepseek.md 2025-09-05 10:58:52 +08:00
gemini.md Update gemini.md 2025-09-05 10:58:57 +08:00
google_vertex_ai.md Update google_vertex_ai.md 2025-09-05 10:59:04 +08:00
grok_xai.md Update grok_xai.md 2025-09-05 10:59:11 +08:00
groq.md Update groq.md 2025-09-05 10:59:27 +08:00
kimi.md Update kimi.md 2025-09-05 10:59:32 +08:00
meta_llama.md Update meta_llama.md 2025-09-05 10:59:38 +08:00
mistral.md Update mistral.md 2025-09-05 10:59:43 +08:00
openai.md Update openai.md 2025-09-05 10:59:49 +08:00
openrouter.md Update openrouter.md 2025-09-05 10:59:54 +08:00
README.md Update README.md 2025-09-03 23:51:09 +08:00
together.md Update together.md 2025-09-05 10:59:59 +08:00

LLM Providers — Guardrails, FAQ, and Fix Patterns

🏥 Quick Return to Emergency Room

You are in a specialist desk.
For full triage and doctors on duty, return here:

Think of this page as a sub-room.
If you want full consultation and prescriptions, go back to the Emergency Room lobby.

This page helps you choose between LLM vendors and fix provider-looking bugs that are actually schema, retrieval, orchestration, or eval drift. If you are new, start with the Orientation table and the FAQ. If you are debugging, jump to the Fix Hub.


Orientation: who is who

Provider What it is Typical use case Link
OpenAI GPT-4/4o from OpenAI Inc. Direct API, fastest model access openai.md
Azure OpenAI Microsoft enterprise wrapper for OpenAI models VNet, compliance, enterprise billing azure_openai.md
Anthropic The company behind Claude Safety-focused platform anthropic.md
Claude (Anthropic) The model family from Anthropic Long context, tool use, JSON control anthropic_claude.md
Google Gemini Google DeepMind multimodal models Multimodal chat, reasoning gemini.md
Google Vertex AI Google Cloud AI platform that hosts Gemini and more Pipelines, deployment, governance google_vertex_ai.md
Mistral EU startup with efficient open-weight models (e.g., Mixtral MoE) Cost/perf, open ecosystem mistral.md
Meta LLaMA Meta open-weight model family Local or private deployment, llama.cpp meta_llama.md
Cohere Enterprise NLP API and embeddings RAG stacks, enterprise NLP cohere.md
DeepSeek CN player with infra-optimized long-context models Cost-efficient, long windows deepseek.md
Kimi (Moonshot) CN chat-first models, very large parameter claims Consumer chat focus kimi.md
Groq Hardware vendor: LPUs for transformer inference Ultra-low latency serving (not a model) groq.md
xAI Grok xAI model family X/Twitter integration, general chat grok_xai.md
AWS Bedrock AWS gateway to many models via one API Enterprises already on AWS aws_bedrock.md
OpenRouter Community model aggregator, OpenAI-style endpoint Try many models via one API key openrouter.md
Together AI Aggregator + infra for open weights and fine-tunes Fast hosting, tuning services together.md

FAQ for newcomers

OpenAI vs Azure OpenAI — are they the same?
Same models, different packaging. OpenAI = direct API and fastest releases. Azure OpenAI = Microsoft billing, VNet, compliance, data residency.

Anthropic vs Claude — why two pages?
Anthropic is the company. Claude is the model family. We separate because “platform issues” and “model quirks” often need different fixes.

Gemini vs Vertex AI — what is the relation?
Gemini is a model. Vertex AI is Google Clouds platform that runs Gemini and provides pipelines, eval, and deployment features.

What makes Mistral special?
Efficient open-weights and MoE designs. Good cost/perf. Easy to host in your own infra.

Meta LLaMA vs local LLaMA
Meta releases the weights. Community tools like llama.cpp let you run them locally on CPU or GPU.

Groq LPU vs GPU
GPU is general purpose. LPU is a chip specialized for transformer inference. You get very low latency for chat workloads.

Bedrock vs OpenRouter vs Together
Bedrock is an AWS enterprise gateway. OpenRouter is a community aggregator with OpenAI-style API. Together is an infra host for open weights with training and fine-tune options.


Open these first


Core acceptance targets

  • ΔS(question, retrieved) ≤ 0.45
  • Coverage ≥ 0.70 for the target section
  • λ remains convergent across three paraphrases and two seeds
  • E_resonance stays flat on long windows

Fix Hub — typical provider symptoms → exact fix

Symptom Likely cause Open this
JSON mode breaks, invalid objects Schema too loose or nested tool calls Data Contracts, Logic Collapse
Tool calls loop or stall Agent role drift, missing timeouts Multi-Agent Problems, Role-drift deep dive
High similarity yet wrong snippet Metric mismatch or fragmented store Embedding ≠ Semantic, Vectorstore Fragmentation
Answers flip between runs Prompt headers reorder and λ flips Context Drift, Retrieval Traceability
Hybrid retrievers worse than single Query parsing split, mis-weighted rerank Query Parsing Split, Rerankers
Jailbreaks or bluffing Overconfidence and missing fences Bluffing Controls, Retrieval Traceability

Fix in 60 seconds

  1. Measure ΔS
    Compute ΔS(question, retrieved) and ΔS(retrieved, expected anchor). Stable < 0.40, transitional 0.400.60, risk ≥ 0.60.

  2. Probe λ_observe
    Vary top-k and prompt headers. If λ flips, lock the schema and apply a BBAM variance clamp.

  3. Apply the module
    Retrieval drift → BBMC + Data Contracts
    Reasoning collapse → BBCR bridge + BBAM
    Dead ends in long runs → BBPF alternate paths

  4. Verify
    Coverage ≥ 0.70 on three paraphrases. λ convergent on two seeds.


Quick-Start Downloads

Tool Link 3-step setup
WFGY 1.0 PDF Engine Paper 1) Download 2) Upload to your LLM 3) Ask “Answer using WFGY + ”
TXT OS (plain text OS) TXTOS.txt 1) Download 2) Paste into any LLM chat 3) Type “hello world” to boot

Explore More

Module Description Link
WFGY Core WFGY 2.0 engine, full symbolic reasoning architecture and math stack View →
Problem Map 1.0 Initial 16-mode diagnostic and symbolic fix framework View →
Problem Map 2.0 RAG-focused failure tree, modular fixes, and pipelines View →
Semantic Clinic Index Expanded catalog for prompt injection, memory bugs, logic drift View →
Semantic Blueprint Layer-based symbolic reasoning and semantic modulations View →
Benchmark vs GPT-5 Stress test with full WFGY reasoning suite View →
Starter Village New here, want a guided path Start →

Early stargazers: See the Hall of Fame
GitHub stars Star the repo if this helped. It unlocks more items on the Unlock Board.

WFGY Main   TXT OS   Blah   Blot   Bloc   Blur   Blow