Fresh stories
Anthropic launches free vulnerability scans for critical open-source projects
Anthropic's OSS Scanner provides periodic vulnerability scans with proofs of concept and patches where possible. Initial scans reported 77 critical and 803 high model-rated findings to maintainers.
Google Research releases Harness² for agents to improve their harnesses
Google Research's open-source Harness² lets agents test edits to prompts, skills, hooks and memory around a frozen model. Editor, composer and reflector agents retain verified improvements for later tasks.
Stripe reports Shield scaling improves fraud recall by more than 8%
Stripe reports more than 8% better recall after scaling Shield, with training epochs cut from 24 to 4.8 hours. Agents run experiment loops using documented operational knowledge, while humans select hypotheses.
Exa 3.0 adds cross-result highlights to its search API
Exa 3.0 adds cross-result highlights, a larger index and Lite search at $4 per thousand queries. Artificial Analysis finds dynamic highlights increase task latency compared with standard search.
Anthropic launches free vulnerability scans for critical open-source projects
Anthropic's OSS Scanner provides periodic vulnerability scans with proofs of concept and patches where possible. Initial scans reported 77 critical and 803 high model-rated findings to maintainers.
MiniMax launches M3.1 Flash at $0.15 per million input tokens
M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens. Artificial Analysis scores it at 42, 13 points above M3, at less than half the cost per task.
T3 Connect creator blames failures on Cloudflare tunnel rate limits
Theo attributes T3 Connect failures to tunnel provisioning and decommissioning rate limits, not tunnel counts. He says broken alerts hid the severity and reports service recovery.
Google Research releases Harness² for agents to improve their harnesses
FastVideo releases a four-bit video generation stack that cuts weights to 30 GiB
Inception launches Mercury 3 with a 1-million-token context window
Stripe reports Shield scaling improves fraud recall by more than 8%
Top storiesthis week
DeepSeek V4.1 Flash 1017 ranks ahead in independent open-model tests
Browser Use, Parallel and Arena report leading open-model results for DeepSeek V4.1 Flash 1017 across browser, search and web-development tests. Practitioner reports show mixed coding reliability.
OpenAI refunds credits stolen in the OpenCode attack
OpenAI says it restored access for affected OpenCode customers and refunded stolen credits. OpenCode's developer says Daybreak was critical to the response after other models began refusing investigative work.
Matt Pocock's pre-commit hook caps agent-written files at roughly 5,000 tokens
Matt Pocock's pre-commit hook rejects staged files above roughly 5,000 tokens, with generated-file exclusions and split instructions. A related skill requires existing oversized files to shrink with each commit.
Kevin Kern coordinates parallel coding agents with file ownership
Kevin Kern describes Opus coordinating Codex workers in separate clones and branches. An integrator checks changed paths before cherry-picking and escalates file-ownership violations to the orchestrator.
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.