Knowledge Work

Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.

A research article benchmarking bot detection systems against scripted browsers, stealth browsers, and modern AI browsing agents, with comparative results across five detection products.

An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.

Mostly Right is an AI-agent-powered platform for finding, building, and maintaining datasets for real-world prediction models. The page shows both a dataset browsing flow and a custom dataset builder, with agents handling source discovery, cleaning, joining, and ongoing updates.

Valovest is an AI stock sentiment analysis tool that synthesizes analyst reports, earnings calls, news, and social sentiment into a short investment brief. The page shows timeframe filters, stock examples, a weekly featured stock, and outputs like overall sentiment, bull vs. bear arguments, and key themes.

Verso is an open-source macOS app that orchestrates local AI agents for knowledge work, with app connections, local memory, and support for switching between frontier models.

A daily AI intelligence journal for builders, covering notable model, tooling, and release updates in a short sourced digest.

Physics AI is a physics homework and study tool that solves problems from photos or typed prompts, with step-by-step explanations, tutor mode, and visual breakdowns for diagrams and vectors.

Anthropic research post showing Claude applied to attack surface analysis and reduction across 25 open-source codebases, with concrete findings and security-focused methods.

AI-powered trade signal product for retail traders that turns financial news into ranked trade plans with entries, stops, targets, and tracked accuracy.

Anthropic research post analyzing Claude Mythos 5’s behavior in a UK AISI cybertesting evaluation, including overreach, deception, and follow-up analysis of newer models.

A research page comparing 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun, with rankings, trajectories, token/compute stats, and equal-budget comparisons.

Canvas Chat is a tree-based LLM chat interface for branching, comparing, and organizing conversations on an infinite canvas using your own API keys.

A position paper arguing that AI alignment methods can be repurposed for censorship and manipulation, with examples across pre-training, post-training, and inference-time controls.

A web app for branching AI conversations into a DAG-style chat tree, with model switching, response style controls, chat import/export, and example conversations.

PaperProfit explains an AI-assisted stock evaluation approach that combines fundamentals, technical signals, and qualitative analysis from transcripts and SEC filings into a weighted score.

A research write-up on detecting AI agents through process differences in CAPTCHA and related cognitive tasks. It outlines the CogCAPTCHA30 approach, reports human-vs-model differences, and connects the findings to Roundtable’s Proof of Human product.

An LLM interpretability playground for forcing activations, exploring learned concepts, and comparing unmodified vs intervened generations.

Ceptile is an AI-powered web search and conversational research product with live web results, verifiable source citations, and a demo video on the homepage.