Anthropic's beta for mid-conversation tool changes, shipped with Claude Opus 5, fixes a prompt-caching bug that caused cache misses when the `tools` array was modified mid-session, costing up to 87% s…
AI agent systems are driving up model costs because repeated calls across planners, workers, reviewers, and tools multiply expenses, yet many agent tasks—such as email routing, data extraction, and re…
Anthropic is introducing a staged access program for life-science researchers to use its frontier AI systems, beginning with a restricted cohort of biology researchers for the Mythos 5 model. The comp…
Z.ai opened API access to GLM-5.3 on August 18th, charging $1.40 per million input tokens and $4.40 per million output tokens, with the model featuring forced reasoning and improved coding and cyberse…
Anthropic's Claude Fable 5 responses began returning server-signed metadata naming an internal route called 'claude-kettle-e2c95a10-v2-prod' late on August 16th, according to an analysis posted on X b…
Anthropic's Claude AI suffered a widespread outage on August 18, affecting multiple models including Claude Mythos 5, Claude Fable 5, Claude Opus 5, Claude Sonnet 5, and Claude Haiku 4.5, as well as c…
LLM-as-a-Verifier, a framework for fine-grained agent feedback, reports that self-verification with DeepSeek V4 Flash outperforms Claude Fable 5 on Terminal-Bench 2.1, achieving 86.5% ± 1.1% Pass@1 fo…
XAI's Grok 4.6 ranked third on the Artificial Analysis Healthcare and Medical Index, behind Anthropic's Claude Opus 5 (max) and Claude Fable 5 (with fallback), according to a benchmark weighting clini…
OpenAI and Anthropic are restricting access to their most advanced models, including OpenAI's GPT-5.6 and Anthropic's Claude Fable 5 and Mythos 5, amid U.S. regulatory pressure, according to a report.…
Anthropic's Claude Opus 5 has taken the top spot in AI intelligence rankings, with the company leading AI spending at 65 percent, according to market data. The model's cost-effectiveness is noted as a…
DeepSeek overtook Google in token volume on Vercel's AI Gateway by July 2026, with DeepSeek at 25% and Google at 10.7%, according to the Vercel AI Gateway Production Index for August 2026. DeepSeek V4…
Anthropic's published system-prompt history for Claude models shows a sawtooth pattern of growth and pruning, not a monotonic ratchet, with the Opus 5 prompt at about 3,200 words after shrinking for t…
Between October 2018 and July 2026, AI models progressed from simple systems like BERT to massive agents that solve complex math and write software, with the ability to resolve real coding issues impr…
Anthropic's system-prompt release notes for Claude grew from 358 words in July 2024 to 3,235 words by July 2026, a ninefold increase that a developer says offers a playbook for production AI teams. Th…
Z.ai released GLM-5.3 on August 14, 2026, a post-training upgrade of the same 743B Mixture-of-Experts base as GLM 5.2, with major gains in coding and agentic ability and an emergent cybersecurity capa…
DeepSeek V4 Pro 0813 solves 82.7% of DeepSWE tasks at $8.28 each when escalated to Claude Fable 5 only on failure, outperforming Fable alone (69.7% at $21.63) by 13 points at 62% lower cost, according…
Rails' Agents on Rails benchmark added Grok 4.6, GLM 5.3, Gemini 3.7 Flash, and Claude Opus 4.8, with Claude Opus 5 still leading at 58 of 63 tasks. The benchmark now includes 792 runs with full trace…
Google's Gemini 3.7 Flash, released August 13, built a playable browser game from a single prompt in 2 minutes and 13 seconds, a task Gemini 3.6 Flash failed three weeks earlier. The model runs at 75 …
OpenAI and Cerebras announced on August 13 that GPT-5.6 Sol, OpenAI's flagship frontier model, now runs at 750 output tokens per second through a new 'Ultrafast' API tier, 14 times faster than standar…
A software developer at a consultancy ran out of daily AI tokens and was told by his manager to make do, sparking a debate about how companies handle token limits for roles that rely heavily on AI age…