← back
10x Development: LLMs For the working Programmer - Manuel Odendahl
Takeaway
Become a 10x engineer by treating the LLM as a translation/word-simulation engine and using concrete habits like regeneration, response-editing, transcript summarization and ridiculous domain framing.
Summary
- Manuel Odendahl (25-year veteran dev) shares concrete prompting techniques: regenerate 10x rather than 'correcting' the model, edit the LLM's own response to recover from bad output, clear context after 3-4 prompts and restart fresh.
- Core mental model: treat LLMs as translation engines (ticket→code, code→ticket) and as 'word simulators', not as reasoners or agents — this matches how programmers themselves operate.
- Practical hacks: keep custom per-language system prompts (PHP, TS) and swap as needed; ask the LLM to generate one-shot shell-script helpers (e.g., a sed three-liner to strip imports from clipboard); summarize transcripts into READMEs/RFCs to share with teammates instead of forwarding raw chat logs.
- Use 'ridiculous domain' examples (Tolstoy operating system, dinosaur zookeeper) so the model can't lean on your real jargon and is forced to fill structural slots — exposes pattern transfer.
- Skills for the new era: practice, experimentation across models, comfort with non-determinism, and breaking out of the rabbit hole of writing prompts that generate prompts.
prompt-engineeringdeveloper-productivityworkflows
Original description
In this hands-on workshop, learn how Large Language Models (LLMs) can significantly improve your productivity as a software developer. Drawing from three years of experience using LLMs in every aspect of his work as a principal engineer, the presenter will share practical insights and techniques that go beyond simple prompts and off-the-shelf tools. Through a series of interactive exercises and real-world examples, participants will learn how to: Combine classic design patterns, such as domain-specific languages and declarative programming, with transformer-based models Identify the most effective ways to use LLMs for writing software, beyond simply having them generate code Create systems that use LLMs to write software that instructs LLMs to write more software This workshop is designed for engineers and professionals working in software-related fields who want to use LLMs to solve concrete problems and improve their workflow. Attendees will gain valuable insights and practical techniques that they can immediately apply to their projects, regardless of their current level of expertise with LLMs. The presenter, a passionate advocate for "pragmatic programming" with LLMs, has made over 6,000 GitHub contributions using these models in the past year, achieving a high level of quality that demonstrates the technology's potential. Participants need access to a LLM of their choice (recommended: gpt-4o and claude 3.5 sonnet). Please prepare a list of programming topics (projects you want to build, legacy code you might want to work on, frameworks and technologies you want to learn). I will provide an extensive list of ideas to try out during the talk. Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at https://www.ai.engineer/worldsfair/2024/schedule & join us at the AI Engineer World's Fair in 2025! Get your tickets today at https://ai.engineer/2025 About Manuel 25-year software veteran specializing in embedded and systems programming. Heavy user of LLMs for day to day programming. Passionate about scalable, long-term solutions. Driven success in both companies and open-source projects. trusted latent.space discord AI in Action safety fallback (slono)