Tooling26d ago
LiteLLM 1.103.2: forward Claude Code safeguards; attribute CLI session spend; restore pass-through pre-config wins
BerriAI shipped LiteLLM v1.103.2 on 2026-10-01 (PyPI ~06:20Z; 17 commits vs 1.103.1): forward Claude Code safeguards / dangerous-tool-use beta unchanged to Anthropic, Bedrock, Vertex, and Azure AI Foundry so auto mode works behind the proxy; attribute CLI session spend to a per-user cli-session alias for daily activity BI; restore pre-config-wins for pass-through endpoints.
Tooling3d ago
X discussion: Thariq of the Claude Code team says he has left Anthropic; his farewell post drew 24K likes, and a joking "is Opus 5.5 dumber" reply also went viral
On 2026-10-24 (04:04 UTC), Thariq (@trq212), whose X bio reads "Claude Code @anthropicai", posted that he has left Anthropic after more than a year working on Claude Code and plans to take a break before starting something new. When we pulled it, the post had about 24K likes, 2.82M views and 1,800+ replies, with Claude Code colleagues such as Lydia Hallie saying goodbye. About 20 minutes later he replied to Lydia, "wait is it just me or is Opus 5.5 dumber", and that joke drew 8,600+ likes. This is an X discussion and a personal post, not an official Anthropic announcement.
Tooling5d ago
Anthropic guide: fold most subagents back into one main agent loop with on-demand skills and tools; one customer ran about 2x faster
On 2026-10-22, Anthropic's Applied AI team published "Building agents: When to fold subagents into your main agent loop" on claude.com, along with an open-source reference implementation, anthropics/single-agent-loop-kit. The article says that across several enterprise deployments, a single agent with skills frequently beat both the one-big-prompt design and the subagent design on quality, often at lower cost and latency per task; one customer that swapped its multi-agent harness for a single loop saw roughly 2x faster runtime. Anthropic also says it cut Claude Code's system prompt for more advanced models by over 80%. Subagents still make sense in three cases: measurable context bloat, parallel tasks with disposable context, or trouble selecting tools and conflicting instructions. The piece has drawn wide discussion on X over the past two days.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.