AI Intelligence Archive

Laravel AI SDK 1.0 shipped on September 23, and one of the headline features is the Approvable...

You can now use OpenSeal under the Apache License 2.0. It handles the work that grows around an AI...

The standard picture of a cheap AI system is a ladder. Small model at the bottom, big one at the top,...

🧬 The Genesis: Demilitarizing Advanced Oncology for the Masses In modern medical science,...

It's tempting to throw a nutrition question at an LLM and let it produce the numbers. The problem:...

Claude Code Batch File Edits: Using MultiEdit and Write Together to Cut Round-Trips in Long...

Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your...

This is a submission for the Kaggle Benchmarking Challenge. I kept running into the same thing with...

Dia 23 de setembro de 2026, Teatro Carlos Gomes, Blumenau, Santa Catarina. O relógio marcava por...

I've been going through the paces the last month, first a grind while working, then left my job and...

I run a small open-source lab in Switzerland. Most of the code in our repositories is written by AI...

We put an agent on stage in Tokyo and let it pay for MCP tool calls. Follow one request from 'what does this cost?' to the moment the boundary refuses it, with the wire traffic and the checks that make the refusal possible.

I kept looking for a simple way to build small websites with reusable components. Wanted to write...

This one covers two and a half weeks, September 8 to 24. I was out of town for part of it, and the...

Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through inference-time early-stopping mechanisms or by explicitly encouraging s…

We give a gap-free differentially private algorithm for the principal component analysis (PCA) problem with Gaussian data.

Recent literature has shown a strong connection between optimization and sampling. We develop the corresponding first-order theory for diffusion models. First, the SDE-based reverse-time flows of overdamped and underdamped Langevin diffusi…

Three batch commits swept a gated post onto this live site. What broke, why globs did it, and the two checks that now run after every deploy. Readers debate where pipeline gates belong: prose or code.

Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attribute of an AI-generated output aligns with a user-specifie…

Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate. We introduce Belief Self-Distillation (BSD), a unified rea…

Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one model remains difficult: merging the updates in weight space causes interference, retra…

Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic gradient descent can stall near the loss of a constant predicto…

We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it. We introduce a roundtrip benchmark that scores code descriptions by whether code regene…

Decision Transformer performance degrades on long rollouts because the conditioning context drifts out of the training distribution. We show that this drift is visible through the model's own next state prediction error, which rises during…

Uneven rotation and dropped frames make equal-angle assumptions unreliable for turntable reconstruction. We present OC-GS, an object-centric Gaussian splatting that refines each image's angle while maintaining a shared camera, rotation axi…

Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training faces the same challenge: training data is typically construct…

Deep learning has substantially accelerated the calibration of complex stochastic-volatility models, but neural point calibration alone does not capture the uncertainty remaining after an implied-volatility (IV) surface has been observed. …

In my last post, I talked about why AI has become part of my workforce. I have too many things I...

Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integration depends not only on the technology but also on the work teachers do to make it usa…

AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violatin…

We show that neural network weights can be explicilty fintuned to admit a smaller grammar. Weight Pair Encoding (WeightPE) does so by placing a lossy Re-Pair compressor inside a straight-through estimator. The int8 weights of the network a…

Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a framework for analyzing mu…

Large neural networks can be compressed by rounding or "quantizing" their weights to numbers that admit representations with fewer bits. One algorithm for quantization, OPTQ, progressively quantizes the weights of a neural network so that …

Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are …

Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the capture of contextual cues, which are essential for a precise understanding of the conten…

Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multimodal LLMs (MLLMs), which add a third phase, Encode, pose new challenges for resource allo…

TL;DR: A vibe is compressed experience: pattern recognition that shows up as a feeling before it...

I have very, very limited experience with AI agents. I've used AI heavily while building software,...

A 180-degree tablet rotation left ImageAnalysis using an old target rotation. Device logs helped us replace a timing workaround with a verified fix.

When an autonomous agent makes a bad call, the standard architectural reaction is to give it a...