v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cpp11 min read
LobeHub Blog
Stay updated with the latest developments in Artificial Intelligence
Agents on live hardware: reason where you must, engineer everywhere else
CoreWeave Blog10 min read
b11669
llama.cpp1 min read
Saying "Done" Isn’t Enough: How Lobe Eval Tests Agents on Real-World Tasks
Lobe Eval runs agents through LobeHub’s actual product execution path in a stateful, resettable tool environment. Each run is judged using execution traces, tool results, and artifact evidence, while Pass³ measures how often a Case passes in all three runs.
LobeHub Blog13 min read
LOL #18 - Agentic AI Summit at Berkeley, and Pi Joins the Bench
This week at LobeHub: we sponsored Agentic AI Summit 2026 at UC Berkeley and ran a booth in the MLK Building, and Pi joins Codex, Claude Code, Amp, and OpenCode as a coding agent you can connect and drive from LobeHub.
LobeHub Blog2 min read
154 - Client Data Layer: Normalized Entity Graph beyond SWR Cache
Status: Proposed Experimental implementation: Draft PR #17784 TL;DR LobeHub currently uses SWR keys as request identities and, for selected domains, persist...
LobeHub Blog18 min read
LOL #17 - ChatGPT as a Provider, Kimi K3 Fast, and Three Models on One Brief
This week at LobeHub: connect your ChatGPT subscription as a provider with no API key, Kimi K3 gets a low-latency variant, and three frontier models build the same game so you can watch where they diverge.
LobeHub Blog2 min read
LOL #16 - Kimi K3, Grok 4.5, and a Terminal in the Lab
This week at LobeHub: Kimi K3 and Grok 4.5 land in the model picker, a built-in terminal arrives as a Lab experiment you can enable today, and a pro tip turns one sentence into a production-ready motion video.
LobeHub Blog2 min read
How an OAuth Phish Hijacked Our X Account
We break down the OAuth phishing attack that hijacked our X account, how it worked, and what we did next.
LobeHub Blog4 min read
LOL #15 - Fable 5 Is Back, GLM-5.2 Fast, and v2.2.9 Quality-of-Life
This week at LobeHub: Anthropic's Fable 5 is back and ready to use in LobeHub, GLM-5.2 Fast arrives with a side-by-side you have to see, and v2.2.9 lands a round of quality-of-life updates across the platform.
LobeHub Blog2 min read
LOL #14 - AWS Summit, a New Mobile Look, and GLM-5.2 Takes Off
This week at LobeHub: our founders took the stage at AWS Summit China 2026, the mobile app got a fresh new look built for the thumb and the glance, and GLM-5.2, the model we shipped just last week, became one of the most reached-for models on the platform.
LobeHub Blog2 min read
LOL #13 - GLM-5.2, a Glossary, and a CLI for Agents
This week at LobeHub: GLM-5.2 delivers frontier capability at up to 10× lower cost, audio attachments let models that support audio listen, a new top-level Glossary brings order to agent-era jargon, and we sharpen the pitch on a CLI built for agents: no dashboard, no human in the loop.
LobeHub Blog3 min read
LOL #12 - A New Font and 5K on X
This week at LobeHub: the landing site and app move from Harmony Sans to Geist, Workspaces enter internal testing for Team & Enterprise, and we crossed 5,000 followers on X.
LobeHub Blog2 min read
LOL #11 - Drag-Drop Skills, iMessage Beta, and a Home for Coding
Two weeks at LobeHub: platform agents go beta with drag-and-drop skills, iMessage joins the IM gateway, lobehub.com/coding gets a dedicated home, Qwen 3.7 Plus lands, and we welcome a new teammate.
LobeHub Blog3 min read
Build a Harness That Builds Itself
The model alone is no longer the product; the model plus the harness is. Here's how LobeHub uses Agent Operation Tracing to build a harness that improves itself — automated error-pattern inspection, 20+ self-discovered harness bugs, and Agent success rate up from 75% to 95%.
LobeHub Blog14 min read
LOL #10 - Meet the Chief Agent Operator, Product of the Day, and a Repo Incident
This week at LobeHub: Chief Agent Operator (CAO) ships — your agents now operate 7×24 without you online. Plus Product of the Day on Product Hunt and full transparency on a supply chain incident that closed every issue in our repo.
LobeHub Blog3 min read
LOL #9 - Task Ships, and Something Big Next Week
This week at LobeHub: Task turns conversations into trackable, schedulable work assigned to agents — plus a teaser for next week's big launch.
LobeHub Blog2 min read
LOL #8 - Control Coding Agents from LobeHub, Two New Models, and a CLI Home
This week at LobeHub: drive Claude Code and Codex from LobeHub, DeepSeek v4 Pro and GPT Image 2 land, the CLI gets its own landing page, and a sweep of copy refinements across the product.
LobeHub Blog2 min read
LOL #7 - Page Edit History, 10K Commits, and Wording in Interfaces
This week at LobeHub: page edit history ships, our repo crosses 10,000 commits, and René shares an essay on how wording shapes product experience.
LobeHub Blog2 min read
153 - Heterogeneous Agent Runtime: first-class support for external CLI agents (Claude Code, Codex)
Summary Introduce Heterogeneous Agents: a first-class path for driving LobeHub conversations with external agent runtimes (Claude Code today; Codex / Kimi CLI ...
LobeHub Blog6 min read
LOL #6 - Custom Sidebar, Prompt Refinement for Media Gen, and Peerlist Launch
This week at LobeHub: customizable sidebar, inline prompt refinement and translation for image and video generation, and our launch on Peerlist.
LobeHub Blog2 min read
Showing 18 of 30 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from LobeHub Blog
Join 15,000+ AI enthusiasts