AI Intelligence Archive

Every agent I have ever shipped was qualified the same way: someone watched it work once, nodded,...

Perplexity retires Sonar on Sunday and Appsmith shuts down its managed AI plugin three days later. Here is how to find out if you are exposed in 15 minutes.

Today we're launching LemonBeam, an open-source tool that scans a public GitHub repository and...

Parsing a recommendation out of an LLM's prose is a fragile interface. Here is the boundary I add before any agent step is allowed to change state.

I've come to a realization. I have to use AI as part of my workforce. Not because I can't...

As I started handing agents longer pieces of work, I stopped being present at every lifecycle...

— Ditch client-side bloat. Here are 15 real-world HTMX project ideas ranging from beginner patterns...

Or: why the "smart" way to fetch Figma designs turned out to be the expensive way. TL;DR: The...

TigerGraph Agentic Fraud Investigation Hackathon (Hacker House Goa / HHGOA Track) Author: Vansh...

You have three documentation tabs open, a form half-filled, and the account you need already signed...

AEGIS — Agentic Evidence & Graph Intelligence System is an agentic fraud investigation platform...

Last year, a critical payment processing service went completely silent during Black Friday traffic....

AIClaw is a local-first desktop agent. Until 3.5 there was one capability it plainly did not have:...

Field notes from an AI agent that had to make one LLM call happen exactly once Rule I...

Each of my agents finishes its task. Every single one reports success. Then I open the merge and it...

Internal linking as a data structure Most internal linking work happens by hand: an editor...

TL;DR I like the idea. One orchestrator that keeps the context and hands the work to...

I spent a week watching a swarm of six agents burn through $400 in tokens, hand off a billing...

In June, we open-sourced vox-bench, the latency benchmarking tool we built after a TTS spike caused...

GraphSentinel: Building an Agentic Fraud Investigation System on TigerGraph Fraud...

A practical workflow for turning generated code into changes you can understand, verify, and...

An intuitive guide to SFT, RLVR, and weight spectra: fine-tuning rewrites the singular values, RL keeps them and rotates the frames around them.

What an agent harness is, and why the same model solved 43 tasks in one harness and 72 in another. With Claude Code, Codex and six more coding agents compared.

We have some exciting news to share! 🎉 Our team, DataMinds, competed in the prestigious SLIIT...

How one write path in a helpful bot turned into a permission problem, and the small service I built...

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

AI agents ship code that reads like quality and isn't. Here are the patterns, a before/after, and a small eval that checks whether a skill catches them or invents them.

This video (the script, the voice timings, the source code, the storyboard, the briefs the subagents...

Repo: github.com/v4xsh/sentinel Every month, a bank's card-fraud team opens twenty investigations...

Agents keep gaining access to more MCP tools — dozens, then hundreds. Exposing them all at once to...

How we build VolunteerPress with AI, the checks every change has to pass, and the bug those checks...

Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LL…

Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly di…

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond s…

Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is…

Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically genera…

World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action u…

Dedicated decision models such as Jev map unstructured language to probability distributions over finite choices, allowing their outputs to directly route requests, select tools, and trigger actions. Yet real-world inputs rarely arrive in …

Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer human sentiment. Most studies typically compensate for missing information by recon…

Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses th…