🔤 Regular Expressions - tiferrei

🏠HomeLab Blog

spiritcode.blog··Hacker News

ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

💻CLI Tools Code

github.com··Hacker News

AI Academic Brain vs. AI Founder Brain

🧠Apple Neural Engine

fchaubard.github.io··Hacker News

RedEdit: Agentic Red-Teaming of Image Safety Classifiers via MCTS-Guided Photo-Editing

🔐Cybersecurity Academic

arxiv.org·

Show HN: Agam – Activation-based memory for Claude Code, not retrieval

🐋Docker Code

github.com··Hacker News

Self-evolving LLM agents with in-distribution Optimization

🧩Parser Combinators Academic

arxiv.org·

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

✓Automated Theorem Proving Academic

arxiv.org·

Show HN: MCP-gateway-scan read-only scanner for MCP production-readiness

👁️Observability Code

github.com··Hacker News

Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle

🧪Property-Based Testing Academic

arxiv.org·

olivier-ls/php-ruler: A transparent expression & rule evaluator in pure PHP. Strict typing, no dependencies, and an explain mode that shows exactly why a rule passed or failed.

⚙️Compiler Design Code

github.com··Hacker News

The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

🩹Self-Healing Systems Academic

arxiv.org·

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

🔍CBMC Academic

arxiv.org·

ChibiRuby is a pure C# implementation of the mruby virtual machine

⚙️PL Implementation Code

github.com··Hacker News

msalsas/amanuensis: A local-first AI persona for Mastodon and Bluesky — drafts by machine, approved by a human, nothing it can't ground gets published.

🌐ActivityPub Code

github.com··Hacker News

Why grep is failure when it comes to quality and token saving

💻CLI Tools Code

github.com··Hacker News

Show HN: Typedframes – Pandas/polars column name checking at lint time

⚙️Compiler Design Code

github.com··Hacker News

Cznorth/winkterm: AI that shares your terminal session. Open-source AI terminal where the AI types commands directly into your shell, not just suggests them. SSH, Docker, BYO LLM.

💻CLI Tools Code

github.com··Hacker News

GaaraZhu/gate: A deterministic privacy boundary between your data and AI.

🛡️macOS Security Code

github.com··Hacker News

No more posts from tiferrei's subscribed feeds.

Scour all 25257 feeds Learn more about Feeds

Ground Control: A zero-back end admin tool to process 50k records in the browser

Empirical Study for Structured Output Control in LLMs for Software Engineering

Raspberry Pi Home Server: Back Up Your Files Locally for Under $100 DescriçãO

ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

AI Academic Brain vs. AI Founder Brain

RedEdit: Agentic Red-Teaming of Image Safety Classifiers via MCTS-Guided Photo-Editing

Show HN: Agam – Activation-based memory for Claude Code, not retrieval

Self-evolving LLM agents with in-distribution Optimization

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

Show HN: MCP-gateway-scan read-only scanner for MCP production-readiness

Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle

olivier-ls/php-ruler: A transparent expression & rule evaluator in pure PHP. Strict typing, no dependencies, and an explain mode that shows exactly why a rule passed or failed.

The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

ChibiRuby is a pure C# implementation of the mruby virtual machine

msalsas/amanuensis: A local-first AI persona for Mastodon and Bluesky — drafts by machine, approved by a human, nothing it can't ground gets published.

Why grep is failure when it comes to quality and token saving

Show HN: Typedframes – Pandas/polars column name checking at lint time

Cznorth/winkterm: AI that shares your terminal session. Open-source AI terminal where the AI types commands directly into your shell, not just suggests them. SSH, Docker, BYO LLM.

GaaraZhu/gate: A deterministic privacy boundary between your data and AI.