{"slug": "we-all-start-somewhere", "title": "We all start somewhere", "summary": "A developer with 25+ years of experience in Python, PHP, and LAMP stack is transitioning into AI engineering, focusing on local LLMs, offline AI setups, and practical model deployment. The individual aims to build skills in prompting, RAG, fine-tuning, and coding models, seeking community advice on navigating the rapidly evolving AI landscape.", "body_md": "After many years of coding small projects and experimenting with GitHub, mainly around development and pentesting, I’ve found myself increasingly drawn into the AI world.\n\nThe speed at which AI is evolving is honestly fascinating. I’m now looking beyond simply using AI tools and want to properly understand how to build with them from better prompting techniques, to running models locally, to understanding how these systems actually work.\n\nOne of my biggest interests is creating a truly offline AI setup. I’ve been exploring local models, GGUF and abiliterated formats, running models on desktop hardware or even from portable USB/SSD setups, and finding practical alternatives to constantly relying on API keys (especially when experimenting with larger or more capable models can quickly become expensive). So looking for new models to run, or potentially learn to build.\n\nThere is so much happening right now across:\n\nlocal LLMs\n\ncoding models\n\nimage/video generation\n\ntext-to-image and text-to-video workflows\n\nmultimodal models\n\nfine tuning and custom models\n\nRAG systems and private knowledge bases\n\nThe amount of choice is both exciting and overwhelming.\n\nA little background:\n\nI’ve been developing for 25+ years across a range of technologies, including:\n\nPython\n\nPHP / Laravel\n\nVue.js / jQuery\n\nLAMP stack\n\nMySQL\n\nNoSQL databases\n\nElasticsearch / Lucene\n\nlegacy web systems and application development\n\nI’m now looking to add AI engineering to that skill-set not just as a user, but by learning how to build, evaluate, run, and optimise models.\n\nMy current goals are:\n\nunderstanding the best ways to instruct models\n\nlearning when to use prompting vs RAG vs fine tuning\n\nbuilding local AI assistants\n\nexperimenting with coding models\n\ncreating private/offline AI workflows\n\nunderstanding the practical side of deploying AI systems\n\nI’d love to hear from the community", "url": "https://wpnews.pro/news/we-all-start-somewhere", "canonical_source": "https://discuss.huggingface.co/t/we-all-start-somewhere/177233#post_1", "published_at": "2026-06-29 10:17:45+00:00", "updated_at": "2026-06-29 12:38:54.582991+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-infrastructure", "ai-research", "developer-tools"], "entities": ["GitHub", "Python", "PHP", "Laravel", "Vue.js", "MySQL", "Elasticsearch", "Lucene"], "alternates": {"html": "https://wpnews.pro/news/we-all-start-somewhere", "markdown": "https://wpnews.pro/news/we-all-start-somewhere.md", "text": "https://wpnews.pro/news/we-all-start-somewhere.txt", "jsonld": "https://wpnews.pro/news/we-all-start-somewhere.jsonld"}}