You’re way more advanced at OpenClaw than I am but I’ve been having good results still. I have basically a “Table of Contents” type md file… It has a list of “when talking about [topic], reference this md file.” This TOC md file is loaded into context with each chat and is
PROMPT ENGINEERING
-
Essential LLM Fine-Tuning Techniques to Master
By
–
LLM fine-tuning techniques I'd learn if I were to customize them:
— Akshay 🚀 (@akshay_pachaar) 17 avril 2026
Bookmark this.
1. LoRA
2. QLoRA
3. Prefix Tuning
4. Adapter Tuning
5. Instruction Tuning
6. P-Tuning
7. BitFit
8. Soft Prompts
9. RLHF
10. RLAIF
11. DPO (Direct Preference Optimization)
12. GRPO (Group Relative… pic.twitter.com/EiUmhJVQjdLLM fine-tuning techniques I'd learn if I were to customize them: Bookmark this. 1. LoRA
2. QLoRA
3. Prefix Tuning
4. Adapter Tuning
5. Instruction Tuning
6. P-Tuning
7. BitFit
8. Soft Prompts
9. RLHF
10. RLAIF
11. DPO (Direct Preference Optimization)
12. GRPO (Group Relative -
Claude’s System Changes Causing User Frustration on Cowork
By
–
I don't know what Claude did to Cowork's system prompt, but God, that's annoying. Some skills it could always do, but now it keeps on saying "are you sure, because it is too long to do?" However, you prompt it. I understand they may want to reduce the workload, as popularity
-
Microsoft MEMENTO: LLM Reasoning Context Compression Method
By
–
Microsoft just mass-compressed LLM reasoning. their new paper introduces MEMENTO, a method that teaches reasoning models to manage their own context. instead of letting chain-of-thought grow into a flat 32K-token stream, the model learns to segment its reasoning into blocks,
-
User Frustrated by Opus 4.7 Performance Degradation
By
–
super frustrated by Opus 4.7. I really loved 4.6, it was my go-to model. It felt like a very good assistant. Opus 4.7, on the other hand, feels like an annoyed employee who only does his job half-heartedly and only when he feels like it.
-
AI Ignoring User Prompts: Behavioral Concerns
By
–
it feels like it just gives a F about your prompt. It does whatever it feels like to do.
-
AI Domain Specialist: Learning from Your Knowledge Base
By
–
Imagine an AI that does not search the open internet. Instead, it only learns from the material you give it. → PDFs
→ research papers
→ slides
→ audio files
→ websites
→ YouTube videos It becomes an expert inside your knowledge base. Not a chatbot. A domain specialist. -
Anthropic Engineer Releases 14-Minute Masterclass on Building Agents
By
–
🚨 This is absolute GOLD.
— Charly Wargnier (@DataChaz) 17 avril 2026
The @AnthropicAI engineer who literally wrote "Building Effective Agents" just dropped a 14-minute masterclass.
saves you months of headaches trying to figure this out alone.
bookmark for the weekend + read @Av1dlive's great guide below 👇 https://t.co/h5TbVmFuEN pic.twitter.com/e4GzZtj9RfThis is absolute GOLD. The @AnthropicAI engineer who literally wrote "Building Effective Agents" just dropped a 14-minute masterclass. saves you months of headaches trying to figure this out alone. bookmark for the weekend + read @Av1dlive
's great guide below -
LLM vs RAG vs AI Agent vs MCP comparison
By
–
#LLM vs. RAG vs. #AIAgent vs. MCP
by @Python_Dv #GenerativeAI #ArtificialIntelligence #MachineLearning #ML -
Agents AI close 90% gap, humans finish remaining 10%
By
–
The last 10% is where taste, brand, and audience awareness live. Agents can close 90% of the gap fast but finishing still belongs to someone who knows what's actually being communicated.