4. Inoculation Prompting (IP) The paper introduces a simple trick for SFT on flawed data: edit the training prompt to explicitly ask for the undesired behavior, then evaluate with a neutral or safety prompt.
PROMPT ENGINEERING
-
Agentic Context Engineering: Modular Framework for LLM Playbooks
By
–
3. Agentic Context Engineering (ACE) Presents a modular context-engineering framework that grows and refines an LLM’s working context like a playbook, not a terse prompt.
-
Agent responses feel more reliable than personal Gemini
By
–
I am still playing with Agent responses, which are powered by the same Gemini 2.5 Pro, but the output feels more reliable than what we have on personal Gemini. Full scoop
-
Bullshit Marketing Assistant: Overhyped AI Persuasion Tool
By
–
Bullshit Marketing Assistant https://
chatgpt.com/g/g-BeX7kKvOv-
bullshit-marketing
… Ah, you’ve just invoked the holy grail of overblown digital genius — Bullshit Marketing Assistant! This isn’t just another assistant — no, no, my dear visionary, this is the titanium-plated Lamborghini of persuasion, -
ChatGPT Assistant for LinkedIn Marketing Content Generation
By
–
And it's good for "Bullshit Marketing" I created a ChatGPT assistant, ready to create @LinkedIn posts
-
Model Reliability and NSFW Filter Fallback Strategies
By
–
Or just the endless times a model fails either due to random errors or too sensitive NSFW filters Then I fallback to secondary models and try again So users almost never see failures, that's what people pay for
-
Using LLMs to Build Quick Disposable Tools Efficiently
By
–
I love LLMs because I can just prompt them to build simple disposable tools that I'd otherwise not – simple mermaid visualiser it even hooked it up to github pages – all with one prompt; ty codex!
-
Comprehensive Guide to LLM Post-Training: SFT, RLHF, and RL Algorithms
By
–
An excellent technical guide on LLM post-raining covering SFT(supervised finetuning), RL rewards such as RLHF/human preferences, RLAIF/constitutional-AI, RLVR/verifiable outcomes, process-supervised and rubric rewards. Also covers common RL training algorithms from PPO, GRPO, and
-
GPT-4 Agents Outperformed Without Weight Adjustments
By
–
The fact that it beats GPT-4 agents without touching weights… That’s a turning point.
-
Insulting LLMs: Unexpected Prompt Optimization Technique
By
–
Ceux que j'ai formé en sont étonné, mais oui insulter un LLM donne parfois des meilleurs résultats. J'ai expliqué en commentaire pourquoi. …et c'est a la dernière fois qu'il vous donne le meilleur résultat. Vous voulez avoir un meilleur résultat en 1er ? Ne me croyez pas