Fresh stories
OpenCode reports a Console breach affecting 1.4% of users
OpenCode says a breach affected 1.4% of Console users, and users report unauthorized provider charges. A maintainer distinguishes Console from OpenCode itself and says refunds are underway.
Theo reports a 27% Gemini cache miss rate in an agent workload test
Theo reports a 27% Gemini cache miss rate that raised costs roughly 50% above expectations and links a reproduction. The visible exchange with Phil Schmid does not establish which endpoint was tested.
DeepSeek releases V4.1-Flash-1017 with a reported 77% DeepSWE score
DeepSeek released V4.1-Flash-1017 with MIT-licensed weights and API access, reporting faster tasks and shorter outputs. Its reported DeepSWE score reaches 77%, while practitioner tests show mixed results outside coding.
OpenCode reports a Console breach affecting 1.4% of users
OpenCode says a breach affected 1.4% of Console users, and users report unauthorized provider charges. A maintainer distinguishes Console from OpenCode itself and says refunds are underway.
vLLM reports 842 tokens per second for Kimi decoding with NVIDIA DSpark
vLLM reports 842 tokens per second at batch one on GB300 NVL72 with DSpark, plus up to 1.8× better P90 interactivity. Engineers dispute describing the implementation as a megakernel.
Agent log audits link unnecessary revisions to token waste, with usage falling to 12.3M
Teortaxes reports that log audits found agents repeatedly tweaking work after completion. Tests with revised Agents.md instructions reduced usage from 49M to 15.5M tokens, with a later run using 12.3M.
Theo reports a 27% Gemini cache miss rate in an agent workload test
Theo reports a 27% Gemini cache miss rate that raised costs roughly 50% above expectations and links a reproduction. The visible exchange with Phil Schmid does not establish which endpoint was tested.
Kitaru replays agent failures without repeating state-changing tool calls
Paulius describes caching tool outputs with Kitaru to reproduce failures in isolated workers without repeating state-changing calls. He used session replay to investigate an unexpected $40 provider bill.
Infisical releases an Agent Proxy that keeps provider keys outside agent machines
Infisical describes an open-source Agent Vault and Agent Proxy setup that keeps keys outside the agent machine. The proxy retrieves credentials from the vault and attaches them to outbound CLI, MCP and model requests.
Top storiesthis week
NVIDIA reports Rubin delivers up to 5.7× GB300 throughput per watt
NVIDIA-submitted AA-AgentPerf results show Rubin delivering up to 5.7× GB300’s throughput per watt across four agentic coding workloads. The results detail per-user speed, power efficiency and serving stacks.
NVIDIA releases Nemotron 3.5 Super VL with 120B parameters and 1M-token context
Nemotron 3.5 Super VL has 120B total parameters, 12B active per token and a 1M-token context window. Ollama and Factory added the model, with Factory reporting improved tool-call parallelism.
OpenRouter launches Armor beta to screen agent tool calls before execution
OpenRouter’s Armor beta uses Jev to check tool calls against rules and user intent before execution. Agents can enable it as a plugin, including for Claude Code auto permissions with other models.
Meta releases 816B-parameter Muse Spark Open with 1M-token context
Meta released Muse Spark Open with 816B parameters and a 1M-token context window. It scores 39 on Artificial Analysis’s Intelligence Index, with launch support from vLLM, Ollama and Together AI.
ORA uses DeepSeek for robot control, reporting 69.2% on RoboTwin
The open ORA harness combines robot descriptions, perception tools and file-backed context. It reports 69.2% on RoboTwin and 81.4% on LIBERO-Pro, alongside preliminary real-arm demos.