Blogsby GlyphCoBuddy on Novita AI: Coding LLM API for Code Generation and Agents
CoBuddy is available on Novita AI as a coding-focused LLM API for code generation, coding assistants, and AI agent workflows.
35 of 800 posts
Tue Jun 926 posts
Announcing vime: A Simple, Stable, and Efficient RL Framework for LLMs
vime connects slime's training stack with vLLM rollouts to provide a simple, stable, and efficient RL post-training pipeline.
Package Firewall: Blocking 8,000+ malicious packages daily
Replit already scans your projects for vulnerable dependencies, and audits your dependencies before you publish. But risk shows up earlier than that, while you are developing, the moment a malicious package gets installed.
The four pillars for AI agent governance at scale
AI agents need governance infrastructure, not just “better models”. Here are the four pillars every enterprise needs to deploy agents safely at scale: identity, authorization, observability, and accountability.
Stop Prompting. Design the Loop
For about two years, the unit of work with a coding agent was the prompt. You wrote a good one, you gave it enough context, you read what came back, and you wrote the next one.
Gremlin: turning open tasks into pull requests
Gremlin is an autonomous engineering agent for small, well-scoped tasks. It uses Mastra for orchestration and OpenCode in a sandbox to turn Sentry issues, Linear tasks, and Slack instructions into reviewable pull requests.
All social media metrics are bad
Picture this: your company's social media team excitedly informs you that stonks are up this month. You can see the screenshots. They're green. Holy…
Blobby's World Cup Bracket Challenge
I vibe-coded a World Cup bracket app with live player stats, AI analysis, and embedded dashboards using Omni, Snowflake CoCo, and Claude in two evenings. Here's a bit about what you can do with it and how I built it.
AI for everyone, with confidence
We've shipped a lot of AI features since the start of 2026. Here's how they fit together, and why the infrastructure around AI matters as much as the features themselves.
Moving away from @expo/vector-icons
We cut our repro app's bundle by 4 MB by switching from @expo/vector-icons to @react-native-vector-icons. Here's why we now recommend the change.
Text-to-SQL is a definition problem: build the canonical model first
Text-to-SQL doesn’t break because models can’t write SQL. It breaks because they don’t know what your data means. Write the meaning down first as a canonical knowledge layer, and use that one spec to both build the model and answer...
How We Moved Discord Voice to the Edge
Moving Discord’s voice and video onto Cloudflare's edge network. Closer servers, lower ping in most regions, and a few real bugs getting there.
Vertiv unveils high-capacity rack platform for AI and high-density IT deployments
Vertiv (NYSE: VRT), a global leader in critical digital infrastructure, today announced the Vertiv Rack Extreme, a next-generation rack designed for the increasing demands of high-performance computing and AI applications.
How Coverwatch uses Temporal to orchestrate AI-powered insurance workflows
Coverwatch runs its AI-powered insurance workflows on Temporal, keeping agents, broker review, and carrier submissions durable through outages.
Gemini 2.5 Flash API - Pricing, Quickstart & Provider Comparison
Overpaying for reasoning you don't need? Learn how to configure Gemini 2.5 Flash API thinking budgets, compare providers, and make your first call in 5 minutes.
A first look at the build economy
A first look at the emerging build economy: who's building software now, where growth is happening, and why 8 in 10 builders plan to monetize.
What We Learned Hiring 33 Engineers in Two Weeks
Earlier this year, we needed to hire a cohort of engineers in Seattle, fast. We had a product launching at our marquee conference, Deploy, a hard deadline, and a clear picture of what the work would actually require.
Fable 5 review: Coding tasks and code review results
See how Fable 5 performs in coding tasks and CodeRabbit’s review tests, including bug coverage, comment precision, and long-running agent behavior.
Exploring the NEW Convex Claude Code Plugin!
A hands-on look at the Convex Claude Code plugin: building a real-time drawing app without mentioning Convex, migrating a Supabase app over, and what's inside the plugin's MCP server and agent.
Looking beyond campaign metrics: 7 marketing success stories
Amplitude helped these seven marketing teams see what customers did after clicking through their campaigns. Here’s how they used that to improve conversion, CLV, acquisition cost, and more.
How QRT powers real-time research and risk management at petabyte scale
How QRT, a cloud-native quantitative investment manager, uses ClickHouse Cloud and ClickStack to power firm-wide research, real-time risk and P&L, and observability at petabyte scale.
+2more from ClickHouse Blog that day
From Chaos to Clarity: How We Built a Unified, Self-Routing Support Ops Ticketing System at Lyft
Written by Atul Gupta, Analytics Manager, LUS Support Ops, Lyft At Lyft, getting operators and riders connected quickly and reliably depends on more than technology, it depends on the teams working behind the scenes to keep that technology...
Migrating Your GitHub CI to Hugging Face Jobs
+1more from Hugging Face Blog that day
Powering the future of robotics in Europe
+2more from Google DeepMind Blog that day
Industrial policy for the Intelligence Age
Explore our ambitious, people-first industrial policy ideas for the AI era, focused on expanding opportunity, sharing prosperity, and building resilient institutions as advanced intelligence evolves.
+2more from OpenAI News that day
Scaling beyond one: How Airbnb evolved its data architecture for a multi-product world
How Airbnb’s data engineers and analytics engineers built a consistent and flexible data modeling framework to support the expansion into Homes, Experiences, and Services.