# \#llms **URL:** https://forum.devtalk.com/tag/llms/3322.md [Latest](https://forum.devtalk.com/latest.md) · [Categories](https://forum.devtalk.com/categories.md) · [Tags](https://forum.devtalk.com/tags.md) --- ## [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… --- ## [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… --- ## [LLMs Can Infer Political Alignment from Online Conversations](https://forum.devtalk.com/t/llms-can-infer-political-alignment-from-online-conversations/248480)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [3 August 2026 11:36 UTC](https://forum.devtalk.com/t/llms-can-infer-political-alignment-from-online-conversations/248480 "2026-08-03T11:36:07Z")
Due to the correlational structure in our traits such as identities, cultures, and political attitudes, seemingly innocuous preferences like following a band or using a specific slang can reveal private traits. This pos… --- ## [AI for Smarties (Smarties)](https://forum.devtalk.com/t/ai-for-smarties-smarties/248422)
**Author:** [@smarties-press](https://forum.devtalk.com/u/smarties-press)\ **Replies:** 0\ **Last updated:** [30 July 2026 21:52 UTC](https://forum.devtalk.com/t/ai-for-smarties-smarties/248422 "2026-07-30T21:52:14Z")
Bertrand Meyer The most important technology of our time — decoded Millions use AI every day. Few understand why it works. ✓ Why large language models work ✓ Why learning replaced rules ✓ What AI means for softwar… --- ## [Context Engineering (Manning)](https://forum.devtalk.com/t/context-engineering-manning/247186)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 1\ **Last updated:** [27 June 2026 01:54 UTC](https://forum.devtalk.com/t/context-engineering-manning/247186 "2026-06-27T01:54:53Z")
Context engineering is the discipline of selecting, organizing, updating, compressing, prioritizing the precise context a model needs to generate accurate responses. This book shows you how to combine well-designed prom… --- ## [Designing AI Agents (Manning)](https://forum.devtalk.com/t/designing-ai-agents-manning/246467)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [28 May 2026 13:53 UTC](https://forum.devtalk.com/t/designing-ai-agents-manning/246467 "2026-05-28T13:53:46Z")
In Designing AI Agents, you’ll learn how to establish agent architectures that manage costs and take governance seriously from day one. This innovative book explores 27 reusable patterns that you can apply to your own a… --- ## [Machines that Think (Manning)](https://forum.devtalk.com/t/machines-that-think-manning/244485)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [11 May 2026 14:08 UTC](https://forum.devtalk.com/t/machines-that-think-manning/244485 "2026-05-11T14:08:56Z")
AI tools like ChatGPT, Claude Code, and OpenClaw produce impressive results that can be shockingly human-like. But are they really thinking? Machines That Think: What it really means for AI to think tackles this complex… --- ## [DeepSeek V4 dropped today — $0.28/M output on 1M context, running on Huawei Ascend. Are you routing workloads to it?](https://forum.devtalk.com/t/deepseek-v4-dropped-today-0-28-m-output-on-1m-context-running-on-huawei-ascend-are-you-routing-workloads-to-it/242498)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 1\ **Last updated:** [25 April 2026 00:18 UTC](https://forum.devtalk.com/t/deepseek-v4-dropped-today-0-28-m-output-on-1m-context-running-on-huawei-ascend-are-you-routing-workloads-to-it/242498 "2026-04-25T00:18:04Z")
DeepSeek just released V4 and the pricing is hard to ignore. V4-Flash: $0.28/M output tokens. V4-Pro: $2.19/M. Both with 1M token context as default. For reference: GPT-4 Turbo is $30/M output. Claude Opus 4.6 is $75/M… --- ## [Build AI-Enhanced Web Apps (Manning)](https://forum.devtalk.com/t/build-ai-enhanced-web-apps-manning/236203)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [3 March 2026 15:12 UTC](https://forum.devtalk.com/t/build-ai-enhanced-web-apps-manning/236203 "2026-03-03T15:12:04Z")
Build AI-Enhanced Web Apps guides you through AI development using only JavaScript and other common web dev skills–no Python or Machine Learning experience required. You’ll learn by working with full-scale AI projects t… --- ## [Rearchitecting LLMs (Manning)](https://forum.devtalk.com/t/rearchitecting-llms-manning/231739)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [28 January 2026 14:59 UTC](https://forum.devtalk.com/t/rearchitecting-llms-manning/231739 "2026-01-28T14:59:20Z")
Rearchitecting LLMs: Structural techniques for efficient models turns research from the latest AI papers into production-ready practices for domain-specific model optimization. As you work through this practical book, y… --- ## [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… --- ## [Your Laptop Isn’t Ready for LLMs. Yet](https://forum.devtalk.com/t/your-laptop-isn-t-ready-for-llms-yet/227511)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [24 December 2025 05:06 UTC](https://forum.devtalk.com/t/your-laptop-isn-t-ready-for-llms-yet/227511 "2025-12-24T05:06:11Z")
The quest to run large AI models locally on an individual’s machine are driving the biggest change in laptop architecture in decades. Read in full here: --- ## [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… --- ## [We're Losing Our Voice to LLMs](https://forum.devtalk.com/t/were-losing-our-voice-to-llms/224256)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [28 November 2025 00:59 UTC](https://forum.devtalk.com/t/were-losing-our-voice-to-llms/224256 "2025-11-28T00:59:30Z")
We are losing something precious in the age of LLMs: our unique voices. Read in full here: --- ## [ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference](https://forum.devtalk.com/t/chunkllm-a-lightweight-pluggable-framework-for-accelerating-llms-inference/220263)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [27 October 2025 11:11 UTC](https://forum.devtalk.com/t/chunkllm-a-lightweight-pluggable-framework-for-accelerating-llms-inference/220263 "2025-10-27T11:11:16Z")
Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention’s quadratic complexity with input tokens. Recently, researc… --- ## [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… --- ## [Learn AI Data Engineering in a Month of Lunches (Manning)](https://forum.devtalk.com/t/learn-ai-data-engineering-in-a-month-of-lunches-manning/214754)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 3\ **Last updated:** [25 September 2025 18:04 UTC](https://forum.devtalk.com/t/learn-ai-data-engineering-in-a-month-of-lunches-manning/214754 "2025-09-25T18:04:03Z")
Learn AI Data Engineering in a Month of Lunches is a fast, friendly guide to integrating large language models into your data workflows. In just 17 short lessons, you’ll learn how AI can help you handle time-consuming d…