RJRatish Jaininblog.ratishfolio.com·28m ago · 6 min readLLM Observability: A Technical Deep DiveHow do you debug an LLM application when the answer is wrong, latency suddenly spikes, or token costs explode? Traditional application monitoring isn't enough. LLM applications require a new layer of 00
YSYuvraj Singhintechwithyuvi.hashnode.dev·2h ago · 9 min readBuilding My First Multi-Agent App Builder with LangGraphI have been working extensively with AI since 2023. Over the last few years, I have built applications using provider APIs, written prompts that could qualify as short essays, worked on context engine00
PKParth Khuntetainpk-blog.hashnode.dev·1h ago · 10 min readYou Added RAG to Your LLM… So Why Is It Still Hallucinating? RAG makes Large Language Models smarter, but not infallible. It gives AI access to external knowledge, yet the quality of its answers still depends on what information it retrieves, how that informati00
TMTejas Mintejas-genai.hashnode.dev·26m ago · 10 min readWhere RAG Fails: Understanding the LimitationsThere's a moment everyone building with LLMs eventually hits. You ask the model about your company's refund policy, or your product docs, or something that happened last month, and it either makes som00
STSakshi Tyagiinsakshityagi.hashnode.dev·5h ago · 3 min readBeyond 1D Data Parallelism: ZeRO, TP, PP, and CPPart 4 of 4 , Scaling LLM Training. Code for the series: github.com/rocks-saka/Scaling-llm-training The previous three posts got us a long way on a single axis: map the memory, recompute activations, 00
BDBhuvesh Dhimaninblog.bhuveshdhiman.com·5h ago · 1 min readSearch built for agents doesn't look like search built for humansIn July 2026, Amazon Bedrock shipped a managed knowledge base built specifically for agentic search, not human search. A human search box expects one query and one ranked list back. An agent needs som00
BDBhuvesh Dhimaninblog.bhuveshdhiman.com·5h ago · 1 min readMost coding agents run setup instructions without asking a single questionA published exploit chain shows exactly why that habit is dangerous. A coding agent pointed at a malicious README runs pip install verbatim, against an attacker-controlled package index. The exploit e00
AHAkash Hadagali Persettiinakashpersetti.hashnode.dev·15h ago · 8 min readI Ran terraform validate Inside a Lambda. Two Things Broke.Most agent projects that generate code evaluate it by asking another model whether the code looks correct. I did that for about a week in TerraformAgent before I got tired of it. The failure mode is b00
AKAnil Kambaringenai-architect.hashnode.dev·9h ago · 9 min readWhere RAG Fails: Understanding the Limitations"RAG makes AI smarter, but it doesn't make AI perfect." RAG makes an LLM sound more informed. It does not make it correct. Here's a beginner-friendly look at how RAG works, and the honest list of pla00
RYRavindra Yadavinrvindra.hashnode.dev·1d ago · 8 min readWhere RAG Fails: Understand the LimitationsProblem statement - Why? Why do we need RAG? Large Language Models (LLMs) are trained on enormous amounts of data, and training them is extremely expensive in terms of time and computational resources01G
