# \#llm **URL:** https://forum.devtalk.com/tag/llm/2990.md [Latest](https://forum.devtalk.com/latest.md) · [Categories](https://forum.devtalk.com/categories.md) · [Tags](https://forum.devtalk.com/tags.md) --- ## [Understanding AI (Manning)](https://forum.devtalk.com/t/understanding-ai-manning/250082)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 3\ **Last updated:** [13 November 2026 15:23 UTC](https://forum.devtalk.com/t/understanding-ai-manning/250082 "2026-11-13T15:23:12Z")
AI is everywhere—from the tools we use at work to the services and products we rely on every day. But keeping up with the terminology, capabilities, and rapid pace of change can be difficult, especially if you’re new to… --- ## [A $63 Mistake in Production: How an AI Agent's Loop Escaped Without Guards](https://forum.devtalk.com/t/a-63-mistake-in-production-how-an-ai-agents-loop-escaped-without-guards/250506)
**Author:** [@T0ha666](https://forum.devtalk.com/u/T0ha666)\ **Replies:** 2\ **Last updated:** [20 October 2026 09:48 UTC](https://forum.devtalk.com/t/a-63-mistake-in-production-how-an-ai-agents-loop-escaped-without-guards/250506 "2026-10-20T09:48:38Z")
An automated trigger fired every two minutes for 8 hours. 243 agent runs. 31M tokens. $63 wasted. The problem: nobody noticed until morning. This is a case study in production safety when AI agents are on the loop — and… --- ## [Claude at Work (Manning)](https://forum.devtalk.com/t/claude-at-work-manning/250503)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [8 October 2026 11:01 UTC](https://forum.devtalk.com/t/claude-at-work-manning/250503 "2026-10-08T11:01:43Z")
The Claude suite of LLM-powered tools and agents from Anthropic has radiacally–and permanently–changed the way technical professionals design and create software. From agentic code generation to assistants that capture … --- ## [AI Recommender Systems (Manning)](https://forum.devtalk.com/t/ai-recommender-systems-manning/250472)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [7 October 2026 12:53 UTC](https://forum.devtalk.com/t/ai-recommender-systems-manning/250472 "2026-10-07T12:53:09Z")
Customers expect fast, accurate suggestions that are perfectly aligned to their preferences, even when they have limited historical data and provide minimal input. AI Recommender Systems gives you a guided tour to the n… --- ## [Harness, not model is what matters most](https://forum.devtalk.com/t/harness-not-model-is-what-matters-most/249542)
**Author:** [@mudasobwa](https://forum.devtalk.com/u/mudasobwa)\ **Replies:** 4\ **Last updated:** [28 September 2026 15:23 UTC](https://forum.devtalk.com/t/harness-not-model-is-what-matters-most/249542 "2026-09-28T15:23:22Z")
Somewhere, right now, a senior engineer is on the verge of a nervous breakdown because his company will not let him switch from Claude to GPT-5.2, or from GPT to Gemini, or from any of them to a locally-hosted llama tha… --- ## [Constraint Decay: The Fragility of LLM Agents in Backend Code Generation](https://forum.devtalk.com/t/constraint-decay-the-fragility-of-llm-agents-in-backend-code-generation/246071)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [27 September 2026 07:02 UTC](https://forum.devtalk.com/t/constraint-decay-the-fragility-of-llm-agents-in-backend-code-generation/246071 "2026-09-27T07:02:49Z")
Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as … --- ## [Why LLMs Rock (or: BooLLMean Logic for the Uninitiated)](https://forum.devtalk.com/t/why-llms-rock-or-boollmean-logic-for-the-uninitiated/249268)
**Author:** [@mudasobwa](https://forum.devtalk.com/u/mudasobwa)\ **Replies:** 0\ **Last updated:** [29 August 2026 14:38 UTC](https://forum.devtalk.com/t/why-llms-rock-or-boollmean-logic-for-the-uninitiated/249268 "2026-08-29T14:38:12Z")
So, instead of wasting my afternoon arguing with anonymous handles on X, I turned to my trusty, soulless assistant and said: “Listen, please expand this truth table for the dulls out there. Make it sarcastic, make it jo… --- ## [Building Specialized AI Systems (Manning)](https://forum.devtalk.com/t/building-specialized-ai-systems-manning/249018)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [21 August 2026 13:19 UTC](https://forum.devtalk.com/t/building-specialized-ai-systems-manning/249018 "2026-08-21T13:19:28Z")
General-purpose models are impressive, but they aren’t always the right fit for domain-specific or mission-critical applications. Prompt engineering and RAG can take you a long way, but there comes a point when a model … --- ## [Escaping the LLM Coding Rat Race](https://forum.devtalk.com/t/escaping-the-llm-coding-rat-race/248710)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 2\ **Last updated:** [12 August 2026 23:10 UTC](https://forum.devtalk.com/t/escaping-the-llm-coding-rat-race/248710 "2026-08-12T23:10:03Z")
There’s only one winner in the AI coding rat race: your inference provider. Read in full here: --- ## [How to prompt LLM?](https://forum.devtalk.com/t/how-to-prompt-llm/248505)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 3\ **Last updated:** [8 August 2026 22:59 UTC](https://forum.devtalk.com/t/how-to-prompt-llm/248505 "2026-08-08T22:59:03Z")
Prompting Techniques Use any one to many according to your knowledge. Roleplay: “Act as a senior database architect. Explain…” “You are a financial advisor speaking to a beginner investor. Explain…” “You’re a finan… --- ## [LLM Customization and Fine-Tuning (Manning)](https://forum.devtalk.com/t/llm-customization-and-fine-tuning-manning/247841)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 1\ **Last updated:** [11 July 2026 22:10 UTC](https://forum.devtalk.com/t/llm-customization-and-fine-tuning-manning/247841 "2026-07-11T22:10:54Z")
LLM Customization and Fine-Tuning is a hands-on playbook for turning a general-purpose open-weights model into a focused, cost-efficient system that’s tailored to your business. Amit Bahree, Weehyong Tok A lot of… --- ## [Build Applications with Local AI Models on a Mac (Manning)](https://forum.devtalk.com/t/build-applications-with-local-ai-models-on-a-mac-manning/247314)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 4\ **Last updated:** [22 June 2026 09:41 UTC](https://forum.devtalk.com/t/build-applications-with-local-ai-models-on-a-mac-manning/247314 "2026-06-22T09:41:59Z")
Build Applications with Local AI Models on a Mac shows you exactly how to build and run a ChatGPT-style assistant entirely on your own Mac—free forever, with zero data leaving your machine. In this practical book, AI au… --- ## [Written language as the shared substrate between literate brains and LLMs](https://forum.devtalk.com/t/written-language-as-the-shared-substrate-between-literate-brains-and-llms/246805)
**Author:** [@wolf4earth](https://forum.devtalk.com/u/wolf4earth)\ **Replies:** 0\ **Last updated:** [31 May 2026 18:46 UTC](https://forum.devtalk.com/t/written-language-as-the-shared-substrate-between-literate-brains-and-llms/246805 "2026-05-31T18:46:55Z")
The structural argument, briefly: literacy installs a cognitive substrate in human brains; LLMs are built entirely on the same kind of substrate. The empirical anchor is Nucci 2026 in Cortex, plus the broader cognitive n… --- ## [The Slavery in XXI Sentury](https://forum.devtalk.com/t/the-slavery-in-xxi-sentury/242978)
**Author:** [@mudasobwa](https://forum.devtalk.com/u/mudasobwa)\ **Replies:** 0\ **Last updated:** [28 April 2026 06:56 UTC](https://forum.devtalk.com/t/the-slavery-in-xxi-sentury/242978 "2026-04-28T06:56:18Z")
Kinda rant on why mediocre developers tend to adore AI assistants. --- ## [AI Agents for Offensive Security (Manning)](https://forum.devtalk.com/t/ai-agents-for-offensive-security-manning/242215)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [22 April 2026 12:50 UTC](https://forum.devtalk.com/t/ai-agents-for-offensive-security-manning/242215 "2026-04-22T12:50:34Z")
AI is changing how offensive security workflows are designed, executed, and analyzed. AI Agents for Offensive Security: AI-powered attacks and how to stop them shows you how to build and use AI agents and multi-agent pi… --- ## [Retrieval Augmented Generation, The Seminal Papers (Manning)](https://forum.devtalk.com/t/retrieval-augmented-generation-the-seminal-papers-manning/236651)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [6 March 2026 12:57 UTC](https://forum.devtalk.com/t/retrieval-augmented-generation-the-seminal-papers-manning/236651 "2026-03-06T12:57:26Z")
Retrieval Augmented Generation, The Seminal Papers explores 12 foundational research papers that explain why RAG works, how it’s built, and what makes it different from other approaches. Ben Auffarth Most enginee… --- ## [Thinking Elixir 289 - Erlang Drives into QNX Territory](https://forum.devtalk.com/t/thinking-elixir-289-erlang-drives-into-qnx-territory/231586)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 1\ **Last updated:** [26 February 2026 11:13 UTC](https://forum.devtalk.com/t/thinking-elixir-289-erlang-drives-into-qnx-territory/231586 "2026-02-26T11:13:58Z")
Episode 289 of Thinking Elixir. News includes a groundbreaking effort to port Erlang to QNX for automotive systems, ExDoc 0.40.0 adding LLM-friendly features, Permit.Phoenix v0.4.0 improving authorization workflows, Oban… --- ## [Introduction to Generative AI, Second Edition (Manning)](https://forum.devtalk.com/t/introduction-to-generative-ai-second-edition-manning/233620)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [11 February 2026 15:07 UTC](https://forum.devtalk.com/t/introduction-to-generative-ai-second-edition-manning/233620 "2026-02-11T15:07:09Z")
Introduction to Generative AI, Second Edition, guides you from your first eye-opening interaction with tools like ChatGPT to how AI tools can transform your personal and professional life safely and responsibly. AI move… --- ## [Thinking Elixir 290 - Postgres Finally Gets Real Search](https://forum.devtalk.com/t/thinking-elixir-290-postgres-finally-gets-real-search/232554)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [3 February 2026 13:26 UTC](https://forum.devtalk.com/t/thinking-elixir-290-postgres-finally-gets-real-search/232554 "2026-02-03T13:26:16Z")
Episode 290 of Thinking Elixir. News includes Elixir v1.20.0-rc.1 with important type system improvements, not one but two new Elixir-native Bash interpreters for seamless interop, LiveCapture bringing zero-boilerplate s… --- ## [Hugging face in Action (Manning)](https://forum.devtalk.com/t/hugging-face-in-action-manning/232374)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [2 February 2026 14:25 UTC](https://forum.devtalk.com/t/hugging-face-in-action-manning/232374 "2026-02-02T14:25:12Z")
Hugging Face in Action reveals how to get the absolute best out of everything Hugging Face, from accessing state-of-the-art models to building intuitive frontends for AI apps. Wei-Meng Lee Hugging Face in Action … --- ## [Phind Has Shut Down](https://forum.devtalk.com/t/phind-has-shut-down/230488)
**Author:** [@Eiji](https://forum.devtalk.com/u/Eiji)\ **Replies:** 2\ **Last updated:** [18 January 2026 00:28 UTC](https://forum.devtalk.com/t/phind-has-shut-down/230488 "2026-01-18T00:28:27Z")
Yesterday a very interesting to discuss situation have happen. While StackOverflow still suffer a lot, because of chat bots, but yesterday was not the end its of the story. However things are completely different for Phi… --- ## [Thinking Elixir 287 - From RAGs to Rich Workflows](https://forum.devtalk.com/t/thinking-elixir-287-from-rags-to-rich-workflows/229834)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [13 January 2026 13:41 UTC](https://forum.devtalk.com/t/thinking-elixir-287-from-rags-to-rich-workflows/229834 "2026-01-13T13:41:57Z")
Episode 287 of Thinking Elixir. News includes Arcana, a new RAG library for Phoenix that adds vector search and AI Q&A using Postgres and pgvector, a JavaScript embedding library called MquickjsEx that brings MicroQuickJ… --- ## [Resources to learn how to compute HMM transition matrix?](https://forum.devtalk.com/t/resources-to-learn-how-to-compute-hmm-transition-matrix/223901)
**Author:** [@j\_0t](https://forum.devtalk.com/u/j_0t)\ **Replies:** 1\ **Last updated:** [17 December 2025 14:58 UTC](https://forum.devtalk.com/t/resources-to-learn-how-to-compute-hmm-transition-matrix/223901 "2025-12-17T14:58:49Z")
Hi everyone, I would like to ask you for some resources to learn how to compute HMM transition matrix and then start coding the solution for a morphosyntactic tagger. Ty in advance --- ## [Thinking Elixir 282 - Type Systems and View Transitions](https://forum.devtalk.com/t/thinking-elixir-282-type-systems-and-view-transitions/225737)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [9 December 2025 13:51 UTC](https://forum.devtalk.com/t/thinking-elixir-282-type-systems-and-view-transitions/225737 "2025-12-09T13:51:01Z")
Episode 282 of Thinking Elixir. News includes cutting-edge research from José Valim and Guillaume Duboc on the data structures powering Elixir’s type system that made v1.19 both stronger and faster than v1.18, Phoenix Li… --- ## [Build a DeepSeek Model (From Scratch) (Manning)](https://forum.devtalk.com/t/build-a-deepseek-model-from-scratch-manning/221495)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 3\ **Last updated:** [28 November 2025 21:20 UTC](https://forum.devtalk.com/t/build-a-deepseek-model-from-scratch-manning/221495 "2025-11-28T21:20:19Z")
In Build a DeepSeek Model (From Scratch) you’ll build your own DeepSeek clone from the ground up. First, you’ll quickly review LLM fundamentals, with an eye to where DeepSeek’s innovations address the common problems an… --- ## [The RLHF Book (Manning)](https://forum.devtalk.com/t/the-rlhf-book-manning/223158)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [18 November 2025 10:44 UTC](https://forum.devtalk.com/t/the-rlhf-book-manning/223158 "2025-11-18T10:44:21Z")
After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In The RLHF Book, AI expert Nathan Lambert gives a true industry insider’s perspective on modern RLHF training pipe… --- ## [Thinking Elixir 278 - WAL-ing Through Database Changes](https://forum.devtalk.com/t/thinking-elixir-278-wal-ing-through-database-changes/222224)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [11 November 2025 13:58 UTC](https://forum.devtalk.com/t/thinking-elixir-278-wal-ing-through-database-changes/222224 "2025-11-11T13:58:33Z")
Episode 278 of Thinking Elixir. News includes the Curiosum Elixir survey closing soon, ReqLLM reaching 1.0 with standardized LLM API support across multiple providers, Isaac Yonemoto’s Codicil library bringing semantic c… --- ## [AI Governance (Manning)](https://forum.devtalk.com/t/ai-governance-manning/222077)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [10 November 2025 14:28 UTC](https://forum.devtalk.com/t/ai-governance-manning/222077 "2025-11-10T14:28:19Z")
AI Governance: Secure, privacy-preserving, ethical systems presents a structured playbook for safely harnessing the potential of Generative AI, including security and privacy, bias, ethics, cost management, and regulati… --- ## [Build an AI Agent (From Scratch) (Manning)](https://forum.devtalk.com/t/build-an-ai-agent-from-scratch-manning/218085)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [9 October 2025 10:13 UTC](https://forum.devtalk.com/t/build-an-ai-agent-from-scratch-manning/218085 "2025-10-09T10:13:00Z")
Build an AI Agent (From Scratch) is a step-by-step guide to creating a working AI agent, starting with the bare essentials and growing your AI into a full-featured, real-world system. Jungjun Hur and Younghee… --- ## [Thinking Elixir Podcast 273: Does the Language Really Matter?](https://forum.devtalk.com/t/thinking-elixir-podcast-273-does-the-language-really-matter/217780)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [7 October 2025 12:19 UTC](https://forum.devtalk.com/t/thinking-elixir-podcast-273-does-the-language-really-matter/217780 "2025-10-07T12:19:56Z")
Episode 273 of Thinking Elixir. News includes Chris McCord releasing a shell-based web browser tool for LLMs extracted from phoenix.new, a new schema validation library called Zoi inspired by JavaScript’s Zod, AshDiagram… [Next page](https://forum.devtalk.com/tag/llm/2990.md?match_all_tags=true&page=1&tags%5B%5D=llm)