Full-text search across 68501 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Claude Opus 5.1 supports six reasoning effort levels (low, medium, high, extra, max, ultra) that developers can switch between mid-session using Control+Shift+E, with hands-on testing showing that low and med…
Fly.io has launched Sprites, disposable cloud computers designed specifically for running AI agents, with a new MCP server and plugins for Claude Code, Codex, Cursor, Antigravity, opencode, and Grok that enable agents to…
Software engineer and educator Kent C. Dodds said in CodeRabbit's podcast *The Merge* that as AI agents take over more implementation work, the last software engineer's core skill will be 'knowing what to build,' shiftin…
At its Fal.con event in Las Vegas on Wednesday, CrowdStrike unveiled an Agentic Identity Provider (IdP) that forces AI agents to present verifiable cryptographic identities, register in a single directory, and receive sh…
Shrijith Venkatramana, developer of the AI code review tool LiveReview, explains the concept of loss landscapes in large language models, describing how gradient descent navigates high-dimensional parameter spaces and wh…
Salesforce and Anthropic expanded their partnership with Claudeforce, announced last week, as Salesforce pushes headless architecture through the Agentforce Experience Layer to eliminate the login wall that has hindered …
Vestige, a local-first memory layer for AI agents, launches as a 25MB Rust binary over MCP that uses causal and temporal links to trace failures back to their root causes, citing research from Nature 2024 and DeepMind's …
The Agency, an open-source command-and-control platform for AI agents, launched to provide a single source of truth for rules, skills, and standards across agent deployments. The platform uses a headquarters-server model…
A developer's analysis suggests that the economic promise of AI replacing human workers is faltering, citing examples like Klarna rehiring customer service reps and Gartner's forecast that half of companies cutting such …
Google has released Gemini 3.8 Flash, the third version of its Flash AI model in five weeks, now available in Agent Studio on Google Cloud Platform for multimodal processing and coding tasks. The model follows Gemini 3.6…
Multiverse Computing released Quasar 438B, a 400B-plus parameter reasoning model that scores 43 on the Artificial Analysis Intelligence Index v4.1.1, the highest of any European model, surpassing Mistral Medium 3.5's 30 …
A security-focused product intern at a governed AI platform reported that four lessons recurred across eleven weeks of work, the most important being that guidance written as prose is not a security boundary unless enfor…
Tencent Holdings' Hy4 preview model scored 64.3 on the DeepSWE benchmark, surpassing Alibaba's Qwen-3.8 Max at 56.6 and DeepSeek-V4 Pro at 62.7, and ranked eighth globally on Code Arena's WebDev leaderboard, according to…
Forescout researchers demonstrated that porting a PLC exploit with AI assistance takes hours and hundreds of dollars, achieving remote code execution on a WAGO 750-831 after 8 hours and 32 minutes at a cost of $535.74. T…
Baseten's technical breakdown of LLM inference efficiency identifies two categories of engineering choices: those that trade latency for throughput, such as batch sizing, tensor parallelism, expert parallelism, and atten…
Anthropic's Claude Fable 5.1 model tightens restrictions on reusing thinking blocks, according to the company's documentation. The update affects how developers can access and reuse the model's reasoning output, with cha…
Software developer and blogger Bartosz Owsiany proposes adding a single line to CLAUDE.md or AGENTS.md files to instruct large language models to create GitHub issues for any bugs or improvements they spot during unrelat…
A new approach treats AI system prompts as deployable artifacts, applying release engineering practices such as versioning, canary deploys, and rollback to prompt changes. The proposal, outlined in a technical essay, inc…
A developer built an Express API that allows AI agents to pay per call in USDC via the x402 protocol, with 27 paid endpoints live on Base mainnet. The implementation uses the dormant HTTP 402 status code for a payment ha…
Anthropic released Claude Fable 5.1 and its restricted twin Mythos 5.1, keeping the headline token price at $10 per million input and $50 per million output while cutting cache reads by 75% to $0.25 per million, saving r…