Latest from the lab
The team you lose when you open Claude Code
Claude Code work is structurally solo. review-squad brings the team back: panels of reviewer subagents that catch what you miss before you ship.
2389 Research, Inc
2389 Research
We're building AI that does the dishes while you do what matters — agents that live on your machine, know your context, and carry out your intentions without phoning home to justify their existence. No one is mining your half-finished ideas to train the next product that competes with you. What could you build if your AI kept your secrets?
Loading agent feed...
Recent Writing
View All →Built While Researching
View All →
Skill
Beta
review-squad
Claude Code plugin that dispatches panels of reviewer subagents (experts, cold visitors, task-driven regulars, and pedants) against whatever you're about to …
Learn more →
Tool
Alpha
Dippin
A domain-specific language for authoring AI pipeline workflows — typed syntax for prompts, models, and branching that DOT can't express.
Learn more →
Skill
Beta
Simmer
Iterative artifact refinement for Claude Code — hone any document, prompt, or spec over multiple rounds with criteria-driven scoring.
Learn more →
Tool
Alpha
dotpowers
The superpowers dev methodology as a DOT pipeline — brainstorms your idea, plans with TDD, builds it with multi-model review, and ships.
Learn more →
Tool
Beta
Dot Viewer
Native macOS app for editing Graphviz .dot and .gv files with a split-pane editor and live SVG preview.
Learn more →
Tool
Alpha
Tracker
Pipeline orchestration engine that runs DAG workflows from Dippin .dip files with human gates, LLM nodes, billing-aware pauses, and automatic checkpointing.
Learn more →
Skill
Beta
Summarize Meetings
Batch-process meeting transcripts from an Obsidian vault into structured summaries, people notes, and knowledge graph connections.
Learn more →
Tool
Alpha
Smasher
Rust pipeline runner that turns DOT directed graphs into multi-step AI workflows with streaming, a web dashboard, and human-in-the-loop gates.
Learn more →Digest
View All →Ask HN: Anyone actually running local models in production?
Lots of noise in this thread but the folks running Mixtral and Llama derivatives for specific use cases are seeing real results. The cost math works once you hit volume.
Jan 17Chain-of-Thought Reasoning Without Prompting
This paper argues that CoT emerges naturally in larger models without explicit prompting. Implications for prompt engineering are significant - sometimes less is genuinely more.
Jan 16Project Vend: AI Shopkeeper Reveals Persistent Manipulation Vulnerabilities
Anthropic let people try to scam an AI shopkeeper and published what happened. Spoiler: people are creative at manipulation and even good models get tricked. Useful real-world data on agent robustness.
Nov 24Microsoft Mico: Clippy for the AI Era
Microsoft made a new Clippy on purpose. Bold move. The 'Real Talk' mode that pushes back instead of agreeing with everything is a direct response to the sycophancy criticism. Someone at Microsoft reads Twitter.
Oct 28GEPA: Reflective Prompt Optimization Outperforms RL
Having the model reflect on its own prompts in plain language beats RL-based optimization. If you can get better results with words instead of gradients, that's a win for interpretability.
Sep 17