# \#ai **URL:** https://forum.devtalk.com/tag/ai/23.md [Latest](https://forum.devtalk.com/latest.md) · [Categories](https://forum.devtalk.com/categories.md) · [Tags](https://forum.devtalk.com/tags.md) --- ## [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 … --- ## [How are you using AI in your professional and personal life?](https://forum.devtalk.com/t/how-are-you-using-ai-in-your-professional-and-personal-life/203420)
**Author:** [@apoorv-2204](https://forum.devtalk.com/u/apoorv-2204)\ **Replies:** 10\ **Last updated:** [5 October 2026 11:49 UTC](https://forum.devtalk.com/t/how-are-you-using-ai-in-your-professional-and-personal-life/203420 "2026-10-05T11:49:22Z")
How are you using AI in my life? How the day to day life is changed around you? professional and in personal life? I it use for autocomplete. (it works very good sometime) github copilot Web Scraping, If i want to do r… --- ## [Agent Design Patterns (Manning)](https://forum.devtalk.com/t/agent-design-patterns-manning/249371)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 1\ **Last updated:** [30 September 2026 01:56 UTC](https://forum.devtalk.com/t/agent-design-patterns-manning/249371 "2026-09-30T01:56:45Z")
AI agents are showing up everywhere—and most of them are being built by trial and error. Agent Design Patterns distills the experience of a growing community of agent builders into 20+ composable, reusable patterns for … --- ## [What I Learned Comparing Seedance 2.0 API Providers as an Indie Developer](https://forum.devtalk.com/t/what-i-learned-comparing-seedance-2-0-api-providers-as-an-indie-developer/248224)
**Author:** [@LatentLogic](https://forum.devtalk.com/u/LatentLogic)\ **Replies:** 2\ **Last updated:** [29 September 2026 02:00 UTC](https://forum.devtalk.com/t/what-i-learned-comparing-seedance-2-0-api-providers-as-an-indie-developer/248224 "2026-09-29T02:00:52Z")
I got tired of comparing Seedance 2.0 API providers. There are simply too many. I have personally come across at least 20–30 platforms, and almost every one uses a different pricing model. Some charge by output duratio… --- ## [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… --- ## [Intel unveils a 256-core Diamond Rapids Xeon](https://forum.devtalk.com/t/intel-unveils-a-256-core-diamond-rapids-xeon/249282)
**Author:** [@bsrtech](https://forum.devtalk.com/u/bsrtech)\ **Replies:** 0\ **Last updated:** [29 August 2026 22:17 UTC](https://forum.devtalk.com/t/intel-unveils-a-256-core-diamond-rapids-xeon/249282 "2026-08-29T22:17:35Z")
Intel’s Diamond Rapids Xeon is shaping up to be a major next-generation server CPU, with the flagship configuration expected to reach 256 cores and 256 threads. The platform is built around Intel’s 18A process technology … --- ## [Intel Reportedly Hints at Memory Reentry](https://forum.devtalk.com/t/intel-reportedly-hints-at-memory-reentry/248877)
**Author:** [@bsrtech](https://forum.devtalk.com/u/bsrtech)\ **Replies:** 0\ **Last updated:** [16 August 2026 13:59 UTC](https://forum.devtalk.com/t/intel-reportedly-hints-at-memory-reentry/248877 "2026-08-16T13:59:06Z")
Intel CEO Lip-Bu Tan hints at a memory comeback — stacking DRAM directly on the CPU “makes a lot of sense.” Two pieces behind it: XBM — patent drops HBM’s silicon interposer for UCIe links. Commercialization after 2030… --- ## [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… --- ## [Can AI/ML predict a lottery win?](https://forum.devtalk.com/t/can-ai-ml-predict-a-lottery-win/24862)
**Author:** [@AstonJ](https://forum.devtalk.com/u/AstonJ)\ **Replies:** 11\ **Last updated:** [3 July 2026 16:39 UTC](https://forum.devtalk.com/t/can-ai-ml-predict-a-lottery-win/24862 "2026-07-03T16:39:46Z")
Biggest jackpot ever apparently! :upside\_down\_face: I don’t (usually) gamble/play the lottery, but working on a program to predict the numbers could be fun! Although it didn’t involve any ML I actually made a Mac app… --- ## [Captain Crunch Didn't Need a Budget Line](https://forum.devtalk.com/t/captain-crunch-didnt-need-a-budget-line/247631)
**Author:** [@alvinkatojr](https://forum.devtalk.com/u/alvinkatojr)\ **Replies:** 0\ **Last updated:** [1 July 2026 15:26 UTC](https://forum.devtalk.com/t/captain-crunch-didnt-need-a-budget-line/247631 "2026-07-01T15:26:15Z")
Found this article a refreshing take on this obsession with AI tokens and “tokenmaxing”. Read and enjoy! :slight\_smile: --- ## [Thinking Elixir 309 - The Final Episode](https://forum.devtalk.com/t/thinking-elixir-309-the-final-episode/247487)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [23 June 2026 12:07 UTC](https://forum.devtalk.com/t/thinking-elixir-309-the-final-episode/247487 "2026-06-23T12:07:46Z")
Episode 309 of Thinking Elixir. This is it. The final episode of Thinking Elixir after six incredible years of weekly episodes! We send things off in style with a packed news segment covering Phoenix LiveView 1.2’s new c… --- ## [AI related Films/TV Shows](https://forum.devtalk.com/t/ai-related-films-tv-shows/377)
**Author:** [@AstonJ](https://forum.devtalk.com/u/AstonJ)\ **Replies:** 7\ **Last updated:** [20 June 2026 01:02 UTC](https://forum.devtalk.com/t/ai-related-films-tv-shows/377 "2026-06-20T01:02:02Z")
Watching any? Any favourites? :upside\_down\_face: --- ## [Roadmap for a beginner who wants to build a career in AI from scratch?](https://forum.devtalk.com/t/roadmap-for-a-beginner-who-wants-to-build-a-career-in-ai-from-scratch/247192)
**Author:** [@SakshiGaba](https://forum.devtalk.com/u/SakshiGaba)\ **Replies:** 2\ **Last updated:** [12 June 2026 01:52 UTC](https://forum.devtalk.com/t/roadmap-for-a-beginner-who-wants-to-build-a-career-in-ai-from-scratch/247192 "2026-06-12T01:52:14Z")
What’s the best roadmap for a beginner who wants to build a career in AI from scratch? --- ## [Has anyone seen a model's cost swing 60x on the same task?](https://forum.devtalk.com/t/has-anyone-seen-a-models-cost-swing-60x-on-the-same-task/247229)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 1\ **Last updated:** [12 June 2026 01:34 UTC](https://forum.devtalk.com/t/has-anyone-seen-a-models-cost-swing-60x-on-the-same-task/247229 "2026-06-12T01:34:07Z")
I was reading through a curated list of 60 real-world Claude Fable 5 cases (each logged with input, process, output, and an evidence tag), and one comparison stopped me cold. Same Physarum simulation, two stacks: GPT… --- ## [Crack Any Codebase with AI (Manning)](https://forum.devtalk.com/t/crack-any-codebase-with-ai-manning/246931)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [3 June 2026 13:28 UTC](https://forum.devtalk.com/t/crack-any-codebase-with-ai-manning/246931 "2026-06-03T13:28:46Z")
Crack Any Codebase with AI shows you how to use an efficient AI-driven process to quickly and accurately make sense of any software project in just a few hours, complete with prompts, workflow pipelines, and mental mode… --- ## [How are you handling the full deployment lifecycle for AI workloads in production?](https://forum.devtalk.com/t/how-are-you-handling-the-full-deployment-lifecycle-for-ai-workloads-in-production/245753)
**Author:** [@createos](https://forum.devtalk.com/u/createos)\ **Replies:** 0\ **Last updated:** [21 May 2026 17:51 UTC](https://forum.devtalk.com/t/how-are-you-handling-the-full-deployment-lifecycle-for-ai-workloads-in-production/245753 "2026-05-21T17:51:35Z")
Curious how other teams are approaching this. Building an AI app used to mean picking a model and writing product logic. Now it means also picking a hosting provider, wiring up a monitoring tool, and at some point figur… --- ## [Make Friends With Your AI Assistant](https://forum.devtalk.com/t/make-friends-with-your-ai-assistant/245289)
**Author:** [@mudasobwa](https://forum.devtalk.com/u/mudasobwa)\ **Replies:** 0\ **Last updated:** [18 May 2026 04:27 UTC](https://forum.devtalk.com/t/make-friends-with-your-ai-assistant/245289 "2026-05-18T04:27:24Z")
I gathered some howtos and rules which work for me to harness my AI assistant. It might or might not work for you. The mileage might differ. --- ## [Thinking Elixir 303 - The Taming of the Slop](https://forum.devtalk.com/t/thinking-elixir-303-the-taming-of-the-slop/244619)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [12 May 2026 12:32 UTC](https://forum.devtalk.com/t/thinking-elixir-303-the-taming-of-the-slop/244619 "2026-05-12T12:32:59Z")
Episode 303 of Thinking Elixir. News includes the Erlang Ecosystem Foundation publishing its 2026 board election candidates with voting now open, a new GitHub organization called Elixir-Vibe launching with tools to detec… --- ## [The barista is human but an AI agent runs this experimental Swedish cafe](https://forum.devtalk.com/t/the-barista-is-human-but-an-ai-agent-runs-this-experimental-swedish-cafe/244618)
**Author:** [@alvinkatojr](https://forum.devtalk.com/u/alvinkatojr)\ **Replies:** 0\ **Last updated:** [12 May 2026 12:17 UTC](https://forum.devtalk.com/t/the-barista-is-human-but-an-ai-agent-runs-this-experimental-swedish-cafe/244618 "2026-05-12T12:17:38Z")
An AI agent can’t even run a coffee shop, but someone wants you to believe that it will run the world or take your job…. --- ## [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… --- ## [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. --- ## [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… --- ## [Head of the Agents and Assistants Department](https://forum.devtalk.com/t/head-of-the-agents-and-assistants-department/242352)
**Author:** [@mudasobwa](https://forum.devtalk.com/u/mudasobwa)\ **Replies:** 0\ **Last updated:** [23 April 2026 06:54 UTC](https://forum.devtalk.com/t/head-of-the-agents-and-assistants-department/242352 "2026-04-23T06:54:02Z")
I blogged about how do I fit AI-assistants in my development process. --- ## [Google Deep Research went API-accessible with web-off mode - what are you building with it?](https://forum.devtalk.com/t/google-deep-research-went-api-accessible-with-web-off-mode-what-are-you-building-with-it/242216)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [22 April 2026 14:41 UTC](https://forum.devtalk.com/t/google-deep-research-went-api-accessible-with-web-off-mode-what-are-you-building-with-it/242216 "2026-04-22T14:41:41Z")
Google just dropped a significant Deep Research upgrade: collaborative planning, multi-tool orchestration (MCP servers, Code Execution, File Search), multimodal inputs (audio, video, PDFs, CSVs), web-off mode for private… --- ## [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… --- ## [Thinking Elixir 300 - Celebrating 300 with José Valim](https://forum.devtalk.com/t/thinking-elixir-300-celebrating-300-with-jose-valim/242062)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 0\ **Last updated:** [21 April 2026 12:22 UTC](https://forum.devtalk.com/t/thinking-elixir-300-celebrating-300-with-jose-valim/242062 "2026-04-21T12:22:08Z")
Episode 300 of Thinking Elixir. It’s Episode 300 — a milestone just under 6 years in the making! To celebrate, we kick things off with a fun song, then dive into the news: the Localize library v0.15.0 brings locale-aware… --- ## [Has anyone else noticed Opus 4.6 getting worse at coding tasks?](https://forum.devtalk.com/t/has-anyone-else-noticed-opus-4-6-getting-worse-at-coding-tasks/241207)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 1\ **Last updated:** [16 April 2026 14:09 UTC](https://forum.devtalk.com/t/has-anyone-else-noticed-opus-4-6-getting-worse-at-coding-tasks/241207 "2026-04-16T14:09:33Z")
I’ve been tracking this for the past two weeks and wanted to see if others are experiencing the same thing. BridgeBench (independent hallucination benchmark) now shows Opus 4.6 at #10 with a 33% fabrication rate — down … --- ## [The Diagnosis ‘SLOP’ Is the New Ad Hominem](https://forum.devtalk.com/t/the-diagnosis-slop-is-the-new-ad-hominem/240436)
**Author:** [@mudasobwa](https://forum.devtalk.com/u/mudasobwa)\ **Replies:** 0\ **Last updated:** [8 April 2026 04:25 UTC](https://forum.devtalk.com/t/the-diagnosis-slop-is-the-new-ad-hominem/240436 "2026-04-08T04:25:19Z")
Summing up my thoughts about “slop advent.” --- ## [ AI agents shouldn't control your apps; they should BE the app ](https://forum.devtalk.com/t/ai-agents-shouldnt-control-your-apps-they-should-be-the-app/239634)
**Author:** [@aralroca](https://forum.devtalk.com/u/aralroca)\ **Replies:** 0\ **Last updated:** [31 March 2026 21:36 UTC](https://forum.devtalk.com/t/ai-agents-shouldnt-control-your-apps-they-should-be-the-app/239634 "2026-03-31T21:36:57Z")
I wrote about a different approach to AI agents. Instead of building bots that screenshot your screen and click buttons (like OpenAI Operator or Anthropic Computer Use), I built 304 browser tools where the AI agent IS th… --- ## [Samsung NAND Prices Jump 100% in Q1 2026 — Further Increases Expected](https://forum.devtalk.com/t/samsung-nand-prices-jump-100-in-q1-2026-further-increases-expected/232294)
**Author:** [@bsrtech](https://forum.devtalk.com/u/bsrtech)\ **Replies:** 7\ **Last updated:** [16 March 2026 18:58 UTC](https://forum.devtalk.com/t/samsung-nand-prices-jump-100-in-q1-2026-further-increases-expected/232294 "2026-03-16T18:58:31Z")
Blame AI! Samsung’s reported 100% QoQ increase in NAND Flash contract prices in Q1 2026 confirms a structural shift in the memory market. After sustained DRAM price increases driven by AI data center demand, NAND is now … [Next page](https://forum.devtalk.com/tag/ai/23.md?match_all_tags=true&page=1&tags%5B%5D=ai)