Tag
#Open source
From Radar
Radar · 2026-06-15
Nathan Lambert leaving Ai2 exposes the fragile side of open models
Nathan Lambert announced his departure from the Allen Institute for AI and used it to reflect on work around Olmo. This is not just a personnel note. It is a reminder that open models depend on institutions that must outlast one strong team.
Read →Radar · 2026-06-15
Holo3.1 pushes computer-use agents from cloud demos to local machines
H Company released Holo3.1, a family of computer-use models for web, desktop, mobile and local inference. The important part is not only higher scores, but the attempt to move the agent closer to where the work actually happens.
Read →Radar · 2026-06-15
Small models show that agentic demos run on boring infrastructure
Hugging Face published a Build Small Hackathon field report about Thousand Token Wood v2, a simulation where four characters run on four different small models. The key lesson for agent systems: serving, JSON repair, secret-data firewalls and bounded memory matter more than poetic prompting.
Read →Radar · 2026-06-14
DOX: a tiny AGENTS.md trick for the big agent-context problem
Agent Zero released DOX, a tiny self-documenting AGENTS.md framework where agents maintain a hierarchy of local instructions before and after code edits.
Read →Radar · 2026-06-09
Claude Fable 5 turns safety into a question of access to the best model
Nathan Lambert reads the Claude Fable 5 release as a dispute over who gets to use a frontier model without routing and filters. The important layer is not only model capability, but the governance system that decides when the user is really talking to the strongest model.
Read →Radar · 2026-06-09
Voice agents break on bilingual calls before they break in polished demos
ServiceNow AI published an ASR benchmark for code-switched speech in enterprise scenarios and tested seven systems. The uncomfortable point is simple: in voice agents, transcription errors propagate through the whole workflow, so bilingual speech is not a minor UX detail.
Read →Radar · 2026-06-03
Reachy Mini gets MCP tools from Hugging Face Spaces
Hugging Face shows Reachy Mini calling MCP tools hosted in public Spaces. The interesting part is not a weather answer, but the split between the robot body and capabilities that can be shared and updated outside the app.
Read →Radar · 2026-06-01
Open models win on cost, but frontier intelligence still sells at a premium
Nathan Lambert argues that open and closed models are improving on different economic curves. The real question is not open source ideology, but where companies will keep paying a premium for the best model.
Read →Radar · 2026-06-01
NVIDIA Cosmos 3 pushes physical AI into one model
NVIDIA released Cosmos 3 on Hugging Face as an open omni-model for world generation, physical reasoning and action generation.
Read →Radar · 2026-05-26
Interconnects maps the next phase of model competition
Nathan Lambert writes about Gemini Flash 3.5, Mythos, agent tools and the tension between open and closed models in his May outlook.
Read →Radar · 2026-05-11
CodexBar unifies limit tracking for 29 AI coding tools in one icon
CodexBar is an open-source macOS menu-bar app that unifies limit tracking, credits, reset windows, and incident status across 29 AI coding providers including Codex, Claude, Cursor, Gemini, Copilot and OpenRouter.
Read →Radar · 2026-04-15
VAKRA benchmark reveals where agents actually fail: tool selection, arguments, multi-step planning
IBM Research published VAKRA: an agent benchmark with 8,000+ real APIs across 62 domains. It evaluates full execution trajectories, not just final answers. Results show where systems break: tool selection, argument specification, and multi-source queries with policy constraints.
Read →From the Glossary