Model
We track 85 posts about Model from 53 engineering blogs. Most active: Vercel, Red Hat, Pinterest. Latest post: Oct 9, 2026.
Companies writing about Model
Recent posts
A Treatise on Model Oriented Programming Languages (opens on the source site)
Thirteen years ago I developed to my knowledge the first and currently the only fully featured model oriented programming language and IDE. I utilized this technology (Mo+) to great effect on my own and workplace enterprise projects, but failed to sell the ideas to a wider audience. Six years ago I left my software engineering career in favor of wielding an ax and building Viking and Anglo Saxon ships in Norway, UK and other future places in Scandinavia. Even so, I still think about model oriented programming from time to time and its potential. The purpose of this article is not about the…
Frontier models found the vulnerabilities. Only the attacker found the chains. (opens on the source site)
Snyk ·
Static analysis found the flaws, but only live attack testing proved how they could be chained into breaches. A comparison of Evo COS, Claude Security, and Claude Code Security.
Route::query() and Model defaults() in Laravel 13.35 (opens on the source site)
Laravel ·
Laravel 13.35 adds Route::query(), an opt-in defaults() method for models, property arrays in fake assertions, percentage worker memory limits, and more. The post Route::query() and Model defaults() in Laravel 13.35 appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox.
Why Telecom Operators Are Building Their AI Strategy on Open Models (opens on the source site)
Nvidia ·
Telecom operators are increasingly building their AI strategies on open models — and the reasons go beyond mere cost. Open models give telcos the ability to trust, control and customize AI across their most critical workloads — from autonomous networks to customer care. NVIDIA’s latest State of AI in Telecommunications report reflects this shift, with […]
Elastic Security and OpenAI GPT Cyber models: What frontier cyber defense means for the public sector (opens on the source site)
Elastic ·
Elastic responded to OpenAI’s call for stronger, faster cyber defense against AI-enabled threats by joining the OpenAI Daybreak Defense Network and announcing plans to integrate OpenAI GPT Cyber models directly into Elastic Security.
Decision Models vs. CVE Data (opens on the source site)
Ollama’s new decision endpoint, Cloudflare’s Clef models on a MacBook, and two questions asked of all 27,489 CVEs published in the last 60 days: does the description say why the bug matters, and is it clear? I read the announcement and had a weekend project before I finished it, because the question I care about ... Read more
Benchmarking AI decision models against traditional guardrails (opens on the source site)
Red Hat ·
As enterprise generative AI applications move to production, platform engineers face a key challenge: balancing the flexibility of LLM-as-a-judge guardrails with the reliability and portability of traditional classifiers that require custom training data. The recent emergence of "decision models"—highlighted by TypeSafe AI's recent announcement of Jev and “System One” models—promises a flexible middle ground by producing fixed “decisions” given a state and a list of questions rather than generating text. The post Benchmarking AI decision models against traditional guardrails appeared first on…
Laya decision model now available on AI Gateway, free through October 31 (opens on the source site)
Vercel ·
Laya from Convai Innovations is free to use on AI Gateway for 1 month through October 31, 2026 via Boundless. Laya is an evaluation/decision model that evaluates shared context against yes/no, choice, or scoring questions and returns structured answers with probabilities. For example, use it to: Triage support requests: Detect a refund request and route it to the billing team. Route agent work: Choose which tool or workflow should handle a request. Check guardrails: Flag a request or response for review when it may violate a policy. Score against a rubric: Rate a ticket's urgency or an…
Microsoft AI models are now available on AI Gateway (opens on the source site)
Vercel ·
Vercel and Microsoft AI (MAI) have partnered to make MAI models available on AI Gateway. AI Gateway is one of a limited number of platforms offering access to MAI models. MAI's focus on security and zero data retention (ZDR) align with Vercel's goal of giving AI Gateway users control over their data and transparency in how it is used for training. MAI models on AI Gateway MAI's latest audio models are now supported on AI Gateway. MAI-Voice-2.1 and MAI-Voice-2.1-Flash generate speech, while MAI-Transcribe-2 Streaming returns transcript updates as audio arrives. MAI-Voice-2.1…
Laravel 14 Adds a defaults() Method to Eloquent Models (opens on the source site)
Laravel ·
Laravel 14 adds a defaults() method to Eloquent models, so default attribute values can use config, feature flags, and dates instead of constant expressions. The post Laravel 14 Adds a defaults() Method to Eloquent Models appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox.
Backdoors in LLMs: Why model scanning isn't enough (opens on the source site)
Red Hat ·
You pull a model from Hugging Face. Maybe you merge in a LoRA. You run benchmarks, spot-check a few completions, and ship it. That workflow assumes the model you tested is the one you'll get in production. The post Backdoors in LLMs: Why model scanning isn't enough appeared first on Red Hat Developer.
Identify AI model overuse with User Insights (opens on the source site)
AI Gateway User Insights now adds task, model, turn, and user categories to help teams understand AI adoption and make better model decisions. This is available free to AI Gateway users.
RAG Complexity Is a Bet Against the Model (opens on the source site)
One Postgres table with two indexes beat every published RAG pipeline on MuSiQue. Every architectural addition is a bet the model stays weak.
Free the models: Harness design at the frontier (opens on the source site)
Replit ·
Model routers are everywhere right now: a small model reads each turn and picks which model should handle it. The inconvenient truth is that the router is always less capable than the model it’s choosing for. Replit Agent lets the model decide instead. The main agent, or core loop, chooses its subagents’ tier and effort, and adjusts its own as the task unfolds. Given that freedom, Astra hands routine implementation to less costly subagents and decides for itself where its tokens are worth spending. On both DeepSWE and Terminal-Bench, Replit Agent is Pareto-efficient against Astra on its own:…
Red team your AI model with garak (opens on the source site)
Red Hat ·
Your team just shipped an internal chatbot built on an open-weight model. It works great! It answers all of your questions, summarizes documents, and helps onboard new hires with scary efficiency. But then your security team asks, “Has anyone tested whether this thing can be jailbroken?”Jailbroken? What's that? The post Red team your AI model with garak appeared first on Red Hat Developer.
We tested our own WAF with frontier AI models. Here’s what we found (opens on the source site)
We built a WAF tester that adapted each request based on what the WAF blocked or passed. This helped us explore variations that a fixed test might miss. We ran it across six attack categories on an authorized staging environment and discovered detection gaps worth fixing. Here’s how the loop worked, what got through, and what we did about it.
How to rank fraud detection models using custom cost metrics (opens on the source site)
Red Hat ·
When building fraud detection systems, standard training steps often hide expensive failures. A model can show 96% accuracy on paper while letting every single fraudulent transaction pass unchecked. In fraud detection, a common first pass uses logistic regression with basic features and a 0.5 threshold. which often yields an accuracy of 96%. The post How to rank fraud detection models using custom cost metrics appeared first on Red Hat Developer.
Run decision models on vLLM and Red Hat AI using DiffusionGemma (opens on the source site)
Red Hat ·
Why Jev went viral, what "System One" models are good for, and how the vLLM community turned DiffusionGemma, already a Red Hat AI validated model, into an open, self-hostable decision engine. The post Run decision models on vLLM and Red Hat AI using DiffusionGemma appeared first on Red Hat Developer.
Route every Claude Code message to the right model with Jev (opens on the source site)
Pulumi ·
Not every message you send to Claude Code needs the most capable model. A quick question about a Git command runs on the same model as a refactor across three services, unless you remember to switch models first. Jev, a new model from TypeSafe AI, can make that decision for you in a few hundred milliseconds and for a fraction of a cent. So I built jev-router, an open source router that asks Jev which Claude model each of your messages needs, and sends it there. What Jev is After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?I’ve spent the last 2…
What we learned running seven AI coding models on real production work (opens on the source site)
Seven AI models read the same ticket and reached the same answer. They were all wrong. The ticket said add a 30-second timeout, so they wrote a 30-second timeout. The engineer … The post What we learned running seven AI coding models on real production work appeared first on Hostinger Blog.
What Dropbox has learned from deploying AI at company scale (opens on the source site)
Dropbox ·
Learnings from deploying AI at company scale, and what organizations need to consider as they move from AI adoption to broader transformation.
Gemini 3.8 text-to-speech models now available on AI Gateway (opens on the source site)
Vercel ·
Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS from Google are now available on AI Gateway. Both models take text and generate speech in more than 100 languages. They support long-form narration, control over delivery, and two-speaker dialogue. google/gemini-3.8-flash-lite-tts is suited to high-volume speech generation, with controls for tone, pacing, and line-by-line delivery. google/gemini-3.8-flash-tts adds voice and character design through natural-language prompts, including acting cues, accents, and conversational reactions. import { experimental_generateSpeech as generateSpeech }…
Tagged Memoized Cache and Model Refreshes in Laravel 13.33 (opens on the source site)
Laravel ·
Laravel 13.33 adds tags to Cache::memo(), a Refreshes attribute for generated columns, AsCollection::nullable(), inplace() index migrations, and more. The post Tagged Memoized Cache and Model Refreshes in Laravel 13.33 appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox.
Building the Operating Model for Agentic AI at Expedia Group (opens on the source site)
Expedia ·
Expedia Group Technology — InnovationHow Expedia Group is getting organizationally and operationally ready for agentsPhoto by Willian Justen de Vasconcellos on UnsplashAt Expedia Group™, agents are showing up across the business: traveler-facing trip planners, partner tools, internal copilots, log readers, and a growing number of workflows that make teams say, “We tried this, and it was surprisingly useful.”That energy is exactly what AI should unlock. But without shared foundations, it can also create fragmented technology choices, partial governance stories, and promising experiments that…
Roonomics: How Economics Helped Us to Build a Churn Prediction Model (opens on the source site)
Why churn prediction matters We partner with thousands of restaurants across our markets to bring our customers an unbeatable selection of food and cuisines. We work hard to find and onboard new restaurants to our platform to improve the customer choice and experience. However, onboarding efforts would be wasted if existing partners were to leave, an event we refer to as churn. We expect there to be some natural level of churn. A restaurant might see low demand because of an adverse economic environment, or the restaurant might be too busy serving on-site customers. Or perhaps the restaurant…
Jev, the model that cannot write a word, and where it fits in web scraping(does it?) (opens on the source site)
Jev by TypeFace AI cannot generate a string, so it cannot extract a field. What it is, how it differs from an LLM, and the one job it earns in a scraping pipeline.
Building Composite Model Context Protocol (MCP) Gateways in TypeScript (opens on the source site)
Build a unified Model Context Protocol (MCP) gateway in TypeScript that aggregates upstream MCP servers, resolves tool collisions, and handles auth and rate limits. Continue reading Building Composite Model Context Protocol (MCP) Gateways in TypeScript on SitePoint.
MiMo V2.6 models now available on AI Gateway (opens on the source site)
Vercel ·
MiMo V2.6 Pro, MiMo V2.6 Flash, and MiMo V2.6 Pro UltraSpeed from Xiaomi are now available on AI Gateway. MiMo V2.6 combines coding, reasoning, and tool use with native text, image, audio, and video understanding. Its 1M token context supports long repositories, tool traces, and multi-session agent work, with structured outputs and up to 128K output tokens. Choose a model based on the workload: xiaomi/mimo-v2.6-pro is the larger sparse mixture-of-experts checkpoint, with 1.02T total parameters and 42B activated per token, for complex software engineering and long-running agent work.…
Jev is the fastest-adopted model in AI Gateway history (opens on the source site)
Vercel ·
Within 24 hours of launching on AI Gateway, Jev from TypeSafe AI reached more than twice as many paid teams as any previous model launch, making it the fastest-adopted model in gateway history. Jev passed every other comparison model in its first twelve hours and continued to widen its lead for the rest of the day. By hour 24, it was being used by nearly 13% of paid teams. That’s 2x as many as the GPT-5.6 family and over 6x as many as Fable 5.1. Jev’s launch shows how quickly a specialized model can find a place in production. Its first-day adoption was unmatched among recent launches; the…
Beyond Two Towers: Launching the 3-Tower Engagement Co-Train Model (Part 2) (opens on the source site)
Authors: Longyu Zhao (Staff Machine Learning Engineer), Gwendolyn Zhao (Staff Machine Learning Engineer), Peng Yan (Senior Machine Learning Engineer), Yuanlu Bai (Senior Machine Learning Engineer), Yuan Wang (Senior Machine Learning Engineer), Yao Cheng (Staff Machine Learning Engineer), Ang Xu (Principal Machine Learning Engineer), Zhaohong Han (Manager II, Ads Lightweight Ranking)IntroductionPreviously¹, we launched the next-generation serving stack for standard ads, which we call Nexus. Nexus decoupled candidate generation from scoring and moved us beyond the classic two-tower-only world,…
Related topics
This page is generated automatically from the engineering blogs we follow. Every post links to its source, where it was published. See all sources.