B-IR – An LLM-optimized programming language
Contribute to imjasonh/imjasonh development by creating an account on GitHub.
B-IR – An LLM-optimized programming language launched on January 12, 2026 with 62 votes, #503 of 14,585 launches that month and more than 95% of that year's launches.
In plain words
B-IR is a programming language designed specifically for use with large language models. It optimizes how code is written and processed by AI systems, making it easier for LLMs to generate, understand, and work with programs. The language is intended for developers who want to leverage AI tools for code generation and manipulation while maintaining clarity and efficiency. B-IR is available on GitHub.
written from the facts on this page · September 2026
From the sources
http://articles.imjasonh.com/llm-programming-language.md Jason Hall First published January 11, 2026 This article describes heavy use of LLMs, but the article itself was written completely by me, a human, without LLM augmentation. I'm not a programming language expert by any stretch of the imagination, and you don't have to be either. On the most recent episode of Oxide and Friends, about predictions for 2026 , I was inspired by one prediction in particular. You can listen to it yourself, starting at around 35 minutes in. The transcript says: I have one more [...] but I feel like it might be a too ambitious. I think this is the year we see LLMs have a programming language, which is not…from github.com
Does a similar job
all alternatives →
I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
- SBSome blind hackers are bridging IRC to LMMs running locally2024 · 2mb.codes · ▲201
Find information, resources and relevant links for 2mb.codes. This domain may be for sale.
Why write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Prompts as WASM Programs2024 · github.com · ▲209AICI is a proposed common interface between LLM inference engines (llama.cpp, vLLM, HF Transformers, etc.) and "controllers" - programs that can constrain the LLM output according to regexp, grammar, or custom logic, as well as control the generation process (forking, backtracking, etc.). AICI is based on Wasm, and is designed to be fast (runs on CPU while GPU is busy), secure (can run in multi-tenant cloud deployments), and flexible (allow libraries like Guidance, LMQL, Outlines, etc. to work on top of it). We (Microsoft Research) have released it recently, and would love feedback on the…
- TLTiny LLMs – Browser-based private AI models for a wide array of tasks2023 · tinyllms.vercel.app · ▲142
An application stack Claude coded directly in LLVM IRMar 2026 · github.com · ▲10This repo is the result of a debate about what kind of programming language might be appropriate if humans are no longer the primary authors. Initially the thought was "LLMs can just generate binaries directly" (this was before a more famous person had the same idea). But that on reflection seems like a bad approach because languages exist to capture program semantics that are elided by translation to machine code. The next step was to wonder if an existing "machine readable" program representation can be the target for LLM code generation. It turns out yes. This project is the result of…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
