AI Tools news and analysis on Web Pulse: 19540 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
A developer demonstrated how a single structured prompt with Claude Fable 5 can generate a complete company—including business plan, brand identity, product spec, landing page copy, and launch videos—in under four hours …
Independent testing of Claude Code's effort levels shows that max mode often provides little to no improvement in output quality over default or high settings for most coding tasks, while significantly increasing token c…
Anthropic's Claude Code introduces the /fewer permission prompt, which scans session history to auto-generate a custom allow list of approved tools and actions, balancing speed and control by granting auto-approval only …
Claude Fable 5 can be used as an orchestrator in multi-agent workflows, delegating execution to cheaper models like Opus or Sonnet, cutting token costs by 10x without quality loss. The approach involves using Fable 5 for…
Context rot degrades AI agent output quality when a model's context window reaches 70-80% capacity, causing attention dilution and signal-to-noise loss. Anthropic's Claude Code addresses this with an auto-compact feature…
A new multi-agent workflow pattern uses Fable 5 as an architect for planning and Grok 4.5 as a construction crew for execution, cutting costs by shifting 90% of token spend to cheaper inference. The approach built a 50-d…
A new workflow using Claude Fable 5 enables users to generate 25 complete websites in under an hour by autonomously researching niches on Pinterest, generating visual assets via Higgsfield, scaffolding site code, and dep…
XAI's Grok 4.5, trained on Cursor coding workflow data, now rivals Anthropic's Claude Opus 4.8 on agentic coding benchmarks, forcing teams to reconsider model choices for production pipelines. The comparison highlights d…
Tencent's Hunyuan-3 and Zhipu AI's GLM 5.2 are competing open-weight models for AI agents, with Hunyuan-3 offering a 256K-token context window and MoE architecture, while GLM 5.2 emphasizes tool-use accuracy and agent-re…
A new analysis distinguishes personal AI agents built for individual use from production AI agents designed for multiple users, highlighting that Markdown-based workflows fail at scale due to structural limitations in ha…
A new workflow combines Remotion, a React-based video framework, with Anthropic's Claude Code coding agent to generate animated logo reveals and motion graphics from text prompts. By installing a Remotion Best Practices …
OpenAI released GPT-5.6 models Sol and Terra, now available in Conductor. Sol is the new flagship model, while Terra is designed for balanced everyday tasks.
AI-generated code now accounts for 51-75% of weekly output at two-thirds of tech firms, with 45% of AI-written code containing security flaws, while the average time from bug disclosure to exploitation has collapsed from…
Google Developer Expert Andriy Lukyanyuk tested Google Antigravity 2.0 with Gemini 3.1 Pro by entering a Kaggle Playground Series competition. The agentic IDE built a pipeline with LightGBM, CatBoost, and a PyTorch MLP, …
OpenAI's GPT-5.6 powers a new version of Charlie, an AI engineering agent that autonomously investigates and resolves stuck PRs, production alerts, and bug reports. The updated system uses three GPT-5.6 models—Sol, Terra…
A new attack exploits Git's support for symlinks to trick AI coding assistants into writing an attacker's SSH key into a victim's authorized_keys file. The technique, which involves committing a malicious symlink to a re…
There is no single best way to structure data for AI agents, according to a new analysis that identifies five production-ready approaches: semantic models, knowledge graphs, RAG, plain markdown files, and open knowledge …
A new benchmark, Long-Horizon Terminal-Bench, evaluates AI agents on 46 terminal tasks across nine categories, including software engineering and scientific computing, using a 90-minute budget and hidden replay-based ver…
A new phenomenon called 'tokenflation' shows AI coding agents using excessive tool calls and reasoning for trivial inputs like 'Hi', costing developers time and money. Benchmarking 14 models revealed that a simple greeti…
SpaceXAI released Grok 4.5, a general-purpose AI model trained alongside Cursor for coding, agentic tasks, and knowledge work, priced at $2 per million input tokens. The model claims superior token efficiency and ranks f…