AI Intelligence Archive

Welcome back to our series on building the ultimate AI research assistant for our AI agent podcast!...

The world of AI agents is moving at lightning speed. Keeping up with the latest trends, new...

Since May I've been building Agent Console, a small desktop app for supervising coding agents —...

A senior software engineer who knew nothing about hardware, a BACnet MS/TP thermostat, and an RS-485 bus. How I ended up with an ESP32-S3 gateway on a DIN rail, wired into Home Assistant, in 15 evenings.

Most people wire up an AI agent and then discover what it can do. I did it the other way round:...

Something broke in your app last night. A checkout flow failed, an LLM call timed out, a vector...

The following scene is a composite on-call pattern, not a personal claim about one employer. A...

My working day spans about ten Git repositories. Here is where their state actually lived: which...

What Broke In the weeks leading up to our most recent production run, our local LLM agent...

Running a local LLM is easy. Running multiple specialized models for coding, reasoning and AI agents...

RL-based post-training for reasoning models is increasingly bottlenecked by repeated fresh rollout generation, particularly in agentic settings where environment interaction dominates wall-clock cost. Replay can reduce this burden by reusi…

Most previous work on speech enhancement (SE) based on masked generative modeling relied on discrete token representations of audio signals, obtained using neural audio codecs (NACs). However, a recent study has shown that continuous laten…

While HTN planning has received significant attention in recent years, support for numerical reasoning remains very limited. In this paper, we investigate numerical Totally-Ordered HTN (TOHTN) planning and show how standard SAT-based encod…

Retrieval-augmented generation (RAG) complements parametric models with retrieved external evidence. The same idea is attractive for continuous-output regression, but directly reusing retrieved target values is often not robust when sample…

Existing research has repeatedly observed the tendency for English loanwords to cluster in the masculine gender across different recipient languages, yet the origin of this pattern remains difficult to determine, as fixed morphological rul…

Generating complete 3D scenes from sparse, unconstrained views is a fundamental challenge in 3D vision which requires reasoning beyond observed content while remaining computationally tractable. Existing feed-forward reconstruction methods…

In online meeting delegation, LLM agents fail to recognize when to speak. With no structured way to track stances, coverage, and floor, they miss the moments where they should contribute. Prompt-only delegates stay silent on 51.4% of the a…

The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneously raising critical concerns about the preservation of fundamental human-centered valu…

Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as \textit{passively} stored facts, leading to sem…

Hierarchical Task Network (HTN) planning is a powerful planning formalism based on task decomposition. Although most of the literature studied plan generation, comparatively less attention has been paid to post-plan optimization. In partic…

We present a comparative evaluation of six information retrieval methods for the task of academic advisor discovery: ranking CS faculty members by relevance to a graduate applicant's research interest statement. The methods span sparse lex…

Continual knowledge-updating methods are often declared superior from one final checkpoint and one conventional adapter rank. We show that this can be insufficient to identify the better operating point. Holding a periodic hierarchy fixed,…

Choosing between Ollama and vLLM is not simply a matter of asking: Which inference engine is...

Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants. Different developers may prefer different models, and individual developers may switch…

3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable in current multimodal large language models (MLLMs). These models falter at precise geometric measurement, at transforming between ego…

CPU steal time is one of those Linux metrics that looks simple until you actually need to diagnose a...

Contact-rich loco-manipulation requires a bridge between semantic action generation and physical interaction control. Existing Vision-language-action (VLA) models generate task-level actions from visual and linguistic observations, but can…

How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three post-training methods - supervised fine-tuning, reasoning-augmented fine-tuning (training …

Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileges yet ship as lifecycle-hook configuration and may fire at…

Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphin…

We introduce Xiaomi-TabLDM, a tabular large data foundation model for classification and regression via in-context learning, which delivers superior prediction accuracy without requiring task-specific fine-tuning. Pretrained exclusively on…

Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample without telling a practitioner which feature ranges made it anomalous. We propose DIFFINT, an autoencoder whose latent bottleneck is structur…

I think a lot of engineers are quietly wondering the same thing right now. “If AI can write the...

AI is Burning Billions. Who Gets the Bill? One company's capital expenditure is another...

This series started with a map and grew into seven pieces. Five layers came first: compute, where...

Most AI agents don't fail because the model is stupid. They fail because engineers treat an agent...

Most AI applications today follow a simple path: User → Application → LLM → Response / Tool...

Part 6 of the Building the AI Memory Stack series At the end of the last article, I left one...

“The stone which the builders rejected, the same is become the head of the corner...” — Matthew...