Stanford researchers built a new prompting technique!By adding ~20 words to a prompt, it:- boosts LLM's creativity by 1.6-2x- raises human-rated diversity by 25.7%- beats fine-tuned model without any retraining- restores 66.8% of LLM's lost creativity after alignmentPost-training alignment methods, such as RLHF, are designed to make LLMs helpful and safe.However, these methods unintentionally cause a significant drop in output diversity (called mode collapse).When an LLM collapses to a mode, it starts favor ...

RT Avi Chawla (@_avichawla)You're in a tech lead interview at Google.The interviewer asks:"AI generates 30% of our code now.But our engineering velocity has only increased by 10%.How would you fill this gap?"You: "Using AI code reviewers will solve this."Interview over!Here's what you missed:Many engineers think the solution to AI bugs is more AI.Their mental model is simple: "If AI can write it, AI can review it."But if AI could catch these issues, why didn't it write correct code in the first place?There' ...

If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs. https://t.co/GrEHuzSgOfAvi Chawla (@_avichawla):You're in a tech lead interview at Google.The interviewer asks:"AI generates 30% of our code now.But our engineering velocity has only increased by 10%.How would you fill this gap?"You: "Using AI code reviewers will solve this."Interview over!Here's what you missed: ...

Learn about AI coding bottlenecks here: https://t.co/hEwlahsyRi ...

You're in a tech lead interview at Google.The interviewer asks:"AI generates 30% of our code now.But our engineering velocity has only increased by 10%.How would you fill this gap?"You: "Using AI code reviewers will solve this."Interview over!Here's what you missed:Many engineers think the solution to AI bugs is more AI.Their mental model is simple: "If AI can write it, AI can review it."But if AI could catch these issues, why didn't it write correct code in the first place?There's enough evidence to sugges ...

RT Avi Chawla (@_avichawla)Context engineering, clearly explained (with visuals):(an illustrated guide below) https://t.co/am97ee4vTA ...

To summarise, I'll leave you with the context engineering graphic.Also, here's an open-source stack for context engineering:- Memory: @zep_ai- Knowledge base: @milvusio- Agent orchestration: @crewAIInc- Observability & tracing: @deepeval https://t.co/qseVsjlXBr ...

4️⃣ Isolating contextIsolating context involves splitting it up to help an agent perform a task.Some popular ways to do so are:- Using multiple agents (or sub-agents), each with its own context- Using a sandbox environment for code storage and execution- And using a state objectCheck this👇 ...

Context engineering, clearly explained (with visuals):(an illustrated guide below) https://t.co/am97ee4vTA ...

RT Avi Chawla (@_avichawla)A popular LLM interview question:"Explain the 4 stages of training LLMs from scratch."(step-by-step explanation below) https://t.co/43WiCQuJfc ...