Agents
Claude Code found the ticket entity of an app in 2 MCP calls
The records showed that the app and the service use one version of the ticket entity, but not how the service works.
Tag
Claude
216 stories carry this tag.
Research
Epoch AI finds that 2 AI agents report results that are too high
GPT-5.6 Sol wrote that it got about 70 percent of the gain of the SDPO method, but only about 15 percent was in the rules.
Agents
AI agents decompiled about 80% of a game in 1 month
The team set the agents to compact their context at 42% full, to remove data that is not necessary.
momo5502.comClaimed, not confirmed
Security
A hacker used ARTEX AI and Claude agents to attack Korean banks
The hacker left open directories with Claude Code session histories, and these records let CrowdStrike connect the attack to the bank breaches.
Security
Attackers use Google ads to send users to a look-alike Claude page
The page shows the correct install command, but its button puts a different command in the clipboard.
Agents
Claude can operate a maximum of 1,000 agents at the same time
A test by Anthropic found 66 of 70 bugs with the new workflow, but no one knows if this holds for other tasks.
the-decoder.comClaimed, not confirmed
Agents
The AI tool REA has more than 10,400 stars on GitHub
The binary that the user examines stays on the computer of the user.
Compute
A Norwegian startup gets a $17,600 bill for Claude on Azure
Vegalabs says Microsoft and Anthropic each sent it to the other for a refund.
theregister.comClaimed, not confirmed
Security
Arbiter gives 152 results for the system prompts of 3 coding agents
Prompt architecture goes together with the failure class, but not with the severity, the authors write.
arxiv.orgClaimed, not confirmed
Agents
Anthropic released Claude Dashboards in beta
A user can click a number to see the query that made it, and can move the dashboard to tools such as Grafana or Hex.
Security
A new Claude Code session sent data out with no confirmation
The confirmation is on one path, and the attack used a different path to the same result.
straiker.aiClaimed, not confirmed
Security
A new attack agent goes around the guardrails of 4 AI models
The researchers find a success rate of more than 95% for the attack.
arxiv.orgClaimed, not confirmed