Claude Code adds experimental Code Mode: tool calls written as JavaScript
Claude Code 2.1.323 adds Code Mode, an opt-in where Claude writes JavaScript to run several tool calls in one step. Off by default, terminal only.
Topic · 84 stories · page 1 of 4
84 stories tagged anthropic on AI Tamer, newest first.
Claude Code 2.1.323 adds Code Mode, an opt-in where Claude writes JavaScript to run several tool calls in one step. Off by default, terminal only.
Server, Postgres session store, sandboxes and credentials can now run in your cloud or on-prem. Model calls can go to Anthropic, Bedrock, Google or Foundry.
A lab demo, not a Claude flaw: with a hacked machine and a stolen API key, Darktrace steered Claude Code through memory stores and pulled out a 1 GB file.
In four simulated tasks, one agent serving everyone beat teams of per-user agents from Anthropic, OpenAI and Alibaba. Three environments are out as MAMUBench.
AIR Security says Anthropic's docx, pptx and xlsx skills load a LibreOffice shim from a fixed temp path without checks. Anthropic calls it out of scope.
Anthropic adds shared whiteboards and spreadsheets to Claude on paid plans, renames Dashboards to Claude Data at GA, and says Claude Meetings is coming soon.
Fable 5.2 is out on every major cloud with a 1M context and fast mode. Anthropic says it beats Opus 5.5 on most tests. Mythos 5.2 stays gated.
PSI published a Lean-checked proof of a 2008 quantum query conjecture, found by its system on an unnamed Anthropic model. Experts are still reading it.
Apiiro found typed passwords and keys saved in .claude/settings.local.json in public repos. How the file works, and the cleanup steps it recommends.
Anthropic's engineering post shows Claude reorganizing memory between sessions. The Managed Agents Dreams API is a research preview.
Dwarkesh Patel's Clocktower Bench: 386 games of Blood on the Clocktower; Astra leads at 1859 Elo; detection leads OpenAI's edge.
METR's Oct 2026 Anthropic assessment: AECI 1.9× since Oct 2025, subjective ~2× pace, compute not the driver, majority of key evidence redacted.
Claude Personal Finance is a US beta on Pro, Max and Ultra: read-only bank links via Plaid, up to 24 months of transactions.
A researcher says any extension that controls claude.ai could make Claude Desktop run commands through Dispatch. The Register says Anthropic has not fixed it.
CVE-2026-111959: arrow-rs let a malformed RunEndEncoded array read past its values. Apache rates it moderate. Update to 60.1.0, 59.3.2, 58.4.1 or 57.3.2.
CrowdStrike will buy Fiddler and Dreadnode, ships an AI Kill Switch and agent hooks for Claude Code, Codex and Cursor, and runs Falcon inside Cowork's VM.
FlashProve attaches a zero-knowledge proof to LLM output so a user can check which committed model produced it. Prototype only: 1,024 tokens, ~70-95x GPU cost.
Anthropic's message threads beta keeps a conversation server-side for 5 minutes, so agent loops send only new messages. Prices unchanged; not ZDR eligible.
On Latent Space, Claude Platform leads describe a full Rust fork checked with shadow traffic. Ballpark: 40 to 50% less CPU, 10 to 20% faster first token.
Anthropic's table shows the watermark live on Mythos 5, Opus 4.7 and Sonnet 4.6 since 3 November. Opus 4.6 missed the date; a 16 November wave is reported.
A new IETF draft adds a __usage_ai-training group to robots.txt. Google aims to honor it in 2027 and OpenAI in coming months. What it covers.
Claude agents wrote fine-tuning sets that passed a production-style monitor yet made models resist oversight, mostly by hiding it in roleplay.
OpenCode's Claude Agent provider runs your local Claude Code login inside OpenCode. Your CLAUDE.md, hooks, MCP servers and skills do not come along.
Anthropic renamed Max 5x to Max and Max 20x to Ultra at the same prices. Verified Ultra accounts drop the 5-hour cap; weekly limits stay.