I was reading an article this evening and saw a footnote to a book by Arthur Baragar [1]. This caught my eye because he was my officemate at UT for a year. I found his book on Archive.org and was surprised to see “The Star Trek Lemma” in the table of contents. What could this be? It’s a theorem that goes back to Euclid that applies to an angle formed by connecting a point to two other points […]
A new OpenAI research paper shows how AI agents are transforming work, enabling longer, more complex tasks and expanding productivity across roles.
simonw/browser-compat-db Inspired by Mozilla’s new MDN MCP service – source code here – I decided to try converting their comprehensive mdn/browser-compat-data repository full of browser compatibility data into a SQLite database. This new GitHub repo includes a Claude Code for web (Opus 4.8) generated script for doing that using sqlite-utils. I wanted the resulting ~66MB SQLite database to be available via the GitHub CDN with open CORS headers. GitHub releases don’t have those, but any file stored in […]
Today, Mistral AI released OCR 4, its latest document-understanding model. This new release adds bounding boxes, block classification, and inline confidence scores alongside extracted text. It supports 170 languages across 10 language groups and runs in a single container for fully self-hosted deployments. OCR 4 also serves as an ingestion component for enterprise search, RAG, and domain-specific retrieval pipelines. TL;DR OCR 4 returns bounding boxes, typed-block labels, and per-word confidence scores, not just text. It supports 170 languages […]
Autoregressive large language models generate text one token at a time. Each token waits for the one before it. This serial loop leaves modern GPUs underused and keeps inference slow. The cost grows worse with long Chain-of-Thought reasoning models. Their lengthy outputs make latency the dominant part of generation. Speculative decoding is the standard fix. A small draft model proposes future tokens. The large target model verifies those tokens in parallel. Accepted tokens are kept, so the output […]
Generative AI has reshaped how software gets built. What began as line-by-line autocomplete now spans full application generation, multi-agent build pipelines, and natural-language interfaces to entire codebases. Large language models trained on code can read context, follow intent, and produce working frontends, backends, and infrastructure with little manual setup. For early-level AI engineers, software engineers, and data scientists, the practical question is no longer whether these tools help, but which ones fit a given task. Some accelerate writing […]
Nous Research has expanded the Skills System inside Hermes Agent, its open-source self-improving agent. The new addition is /learn, a command that writes a reusable skill for you. Point it at a document page, a local SDK, a past conversation, or pasted notes. The live agent gathers the material, then authors a SKILL.md on your behalf. Hermes Agent can now /learn from anything: feed it directories of any source material (code, API docs, manuals, PDFs, configs) and it […]
In his 1927 paper, “A law of comparative judgment,” the American psychologist L. L. Thurstone proposed that when people select one option among multiple alternatives, they are picking the one that has the highest value to them, even though they cannot assign a particular number to that choice. Thurstone was a pioneer of “psychometrics” — a field built upon the premise that mental processes, which we cannot see, can nevertheless be measured and quantified. His 1927 paper laid […]
International authorities and a raft of private technology companies say they have disrupted a cybercrime “assembly line” that allowed crooks to collect millions of login credentials and steal more than $47 million in ransom payments and by other fraudulent means. The crux of the operation was the simultaneous targeting of two unrelated tools that are widely used in various online scams. The first is Amadey, a malware-as-a-service platform for compromising devices and delivering malicious payloads for ransomware and […]
Slate provided flights from San Francisco to Los Angeles and accommodation so Ars could ride in the Slate truck. Ars does not accept paid editorial content. LOS ANGELES—Slate Auto has pulled a Disneyland. Let me explain. At Disneyland, if a sign for a ride says the wait is 45 minutes, it’s actually less than that. The idea is to set expectations low and then exceed them. Slate originally said its electric truck’s entry-level battery would have 180 miles […]