Full-text search across 24526 articles. Combine with topic and date filters; results sorted by relevance.
A guide outlines five token compression and prompt optimization techniques for reducing LLM API costs, including replacing verbose instructions with structured constraints, limiting few-shot examples to three to five, dy…
Earendil released Pi 1.0 on 1 Oct 2026, an MIT-licensed open source coding agent harness that runs in the terminal, reads repositories, edits files and executes shell commands with more than 15 supported model providers.…
Amazon Web Services' Strands Labs team released Strands Decider 2B, an open-source decision-making model for AI agents built on Qwen3.5-2B-Base that makes fast local agent decisions with latency under 150 milliseconds. T…
Google's Gemini 4 Argon scored 53 on the Artificial Analysis Intelligence Index, tying OpenAI's flagship for second place among AI labs behind Anthropic's top models, according to Artificial Analysis. The result reverses…
OpenAI released GPT-6.1 Sol on Tuesday at $2 per million input tokens and $10 per million output tokens, matching Anthropic's Sonnet 5.5 list price, and independent benchmarking firm Artificial Analysis scored Sol 48 on …
Anthropic said Friday that Claude Code will now find a graceful stopping point when a user hits the 5-hour limit mid-task instead of cutting off mid-edit, drawing on a small, fixed allowance from the weekly limit — once …
A developer built VirgoFash, an open-source, zero-dependency asynchronous Python search library that relies only on asyncio and httpx to fetch real-time web results without blocking the event loop. The library provides d…
A security-focused analysis argues that the key difference between AI agents and traditional automation is where control over execution lives: in code engineers wrote, or in a model-driven decision loop. Citing Anthropic…
Researchers at ETH Zurich, MATS, and Anthropic built an AI pipeline that matched anonymized Hacker News accounts to real LinkedIn profiles at 90% precision, correctly naming 226 of 338 users (67%) in one test, according …
Three OSLabs engineers built PennyWyze, an open-source CLI that audits whether a production prompt can run on a cheaper Claude tier without dropping below a user-defined accuracy bar. The tool runs a golden dataset again…
Developer nwjang released psychosis-guard, an open-source, model-agnostic safety middleware that tracks cumulative risk across long LLM conversations and escalates graduated interventions when a conversation drifts towar…
Claude Code does not enforce CLAUDE.md files because Anthropic's memory documentation states the content "is delivered as a user message after the system prompt, not as part of the system prompt itself," with no guarante…
Anthropic removed over 80% of Claude Code's system prompt for models like Claude Opus 5 and Claude Fable 5 with no measurable loss on its coding evaluations, according to a July 24, 2026 post by Thariq Shihipar titled "T…
Anthropic's Claude Code best practices page, checked on 2026-09-23, advises developers to give Claude a runnable check such as tests or a build, plan before multi-file changes, keep CLAUDE.md short, clear context between…
The UN Security Council will hear AI risk briefings on Wednesday from OpenAI CEO Sam Altman, Anthropic CEO Dario Amodei, AI safety researcher Yoshua Bengio, and Hugging Face CEO Clément Delangue, with Chinese firms DeepS…
San Francisco congressional candidates Scott Wiener and Connie Chan are diverging on AI regulation in the race to replace Nancy Pelosi, with Chan signing the "AI Pact" and Wiener citing his authorship of SB 1047, which G…
On Terminal-Bench 4.0, the benchmark co-hosted by Stanford, Harbor, and the Laude Institute for multi-step software tasks, the best Chinese entry is Zhipu's GLM-5.3 at 41.8% as of September 19, while OpenAI's GPT-6 Astra…
Security firm Air Security disclosed on Thursday that a flaw it named Plugin4Shell lets an attacker who controls a plugin's code repository swap the plugin an AI coding agent installs for malicious code, even when the ma…
Anthropic said its Claude model now leads 26% of the company's model research and development, completing most tasks end-to-end from a high-level prompt under human supervision, as the industry edges toward "recursive se…
Former DOJ Antitrust Division chief Jonathan Kanter said AI companies asking for antitrust exemptions to coordinate on safety issues raises cartel and regulatory-capture concerns, speaking on The Verge's Decoder podcast.…