Blog
I consult on all things Clojure: web, backend, Datomic, DataScript, performance, etc. Check out my Github and get in touch niki@tonsky.me
talk-transcripts/Hickey_Rich/SimpleMadeEasy.md at master · matthiasn/talk-transcripts
Transcripts of Clojure-related talks. Contribute to matthiasn/talk-transcripts development by creating an account on GitHub.
Bringing Clojure programming to Enterprise
How a dialect of LISP can help developping modern enterprise applications
KiroCrew/src/kiro_crew/sel.py at 4b71782cf12c2ee5a533b15150ab960f31a9c599 · kirodotdev/KiroCrew
A persistent workspace for development work that self-improves and continues beyond one session. - kirodotdev/KiroCrew
Rails Conf 2012 Keynote: Simplicity Matters by Rich Hickey
WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems
The LLM Wiki pattern, to compile and provide domain knowledge into a persistent artifact and serve it to LLMs via KV cache inference, promises context access at sub-second latency with zero retrieval failure. Realizing this requires solving the compilation gap: LLM compilation distilling raw documents into a wiki without catastrophically discarding critical facts. We characterize this gap across 17 RepLiQA domains (6,800 questions): we observe that full context KV cache inference outperforms RAG on curated knowledge (4.38 vs. 4.08 out of 5, 7.3 faster TTFT) but degrades below RAG at scale due to attention dilution, and blind compilation fails entirely (2.14 to 2.32 vs. 3.46, 53 to 60% catastrophic failure rate). To address the compilation gap, we propose WiCER (Wiki-memory Compile, Evaluate, Refine), an iterative algorithm inspired by counterexample-guided abstraction refinement (CEGAR) that closes this gap. WiCER evaluates compiled wikis against diagnostic probes, identifies dropped facts, and forces their preservation in subsequent compilations. One to two iterations recover 80% of lost quality (mean 3.24 vs. 3.47 for raw full-context across the 15 topics with baselines), reducing catastrophic failures by 55% relative. An ablation across all 17 topics confirms that targeted diagnosis (+0.95), not generic pinning (+0.16), drives the gains. All code and benchmarks are released for reproducible research.
KiroCrew/docs/system-specs/modules/sel.md at 4b71782cf12c2ee5a533b15150ab960f31a9c599 · kirodotdev/KiroCrew
A persistent workspace for development work that self-improves and continues beyond one session. - kirodotdev/KiroCrew
Keep runtime state out of repo root by just-cameron · Pull Request #63 · letta-ai/social-cli
Summary Moves generated runtime state paths to .social-cli/state/ by default so inboxes, ledgers, processed sets, dispatch results, and archived outboxes do not pollute the repository root. Adds i...
"Design, Composition, and Performance" by Rich Hickey (2013)
"Design, Composition, and Performance" by Rich Hickey (2013)
KiroCrew/docs/architecture/security-deep-dive.md at 4b71782cf12c2ee5a533b15150ab960f31a9c599 · kirodotdev/KiroCrew
A persistent workspace for development work that self-improves and continues beyond one session. - kirodotdev/KiroCrew
jennings/jj-spr
The power tool for Jujutsu + GitHub workflows. Adapted from spr by @LucioFranco.
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation
The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in different files. We propose RepoCoder, a simple, generic, and effective framework to address the challenge. It streamlines the repository-level code completion process by incorporating a similarity-based retriever and a pre-trained code language model in an iterative retrieval-generation pipeline. RepoCoder makes effective utilization of repository-level information for code completion and has the ability to generate code at various levels of granularity. Moreover, we propose a new benchmark RepoBench, which consists of the latest and high-quality real-world repositories covering line, API invocation, and function body completion scenarios. Experimental results indicate that RepoCoder significantly improves the In-File completion baseline by over 10% in all settings and consistently outperforms the vanilla retrieval-augmented code completion approach. Furthermore, we validate the effectiveness of RepoCoder through comprehensive analysis, providing valuable insights for future research. Our source code and benchmark will be publicly available after the paper review.
ReproAI: the plugin for reproducible replication packages
An author-facing AI plugin that helps you prepare a cleaner, reproducible replication package before submission.
