Full-text search across 71086 articles. Combine with topic and date filters; results sorted by relevance.
Giles Thomas completed building and training a GPT-2 small model from scratch using JAX, achieving a test loss of 3.418784, outperforming both his PyTorch model (3.538161) and the original GPT-2 small (3.499677). The tra…
FreshSaaS.online, a platform for discovering new software tools, features multiple AI-related launches including deltafin, an open-source project that runs Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Ap…
Parselbox, an embeddable Python sandbox for AI agents, launched on Hacker News, enabling agents to call MCP servers, APIs, and shells as native Python objects in a single Deno and Pyodide process (~160 MB). The tool prov…
AgentRouter, a non-profit OpenAI-compatible API gateway, aggregates over 30 AI models including Claude, GPT, Gemini, and DeepSeek behind a single endpoint, offering new users $200 in free credits via referral. The platfo…
Mean time to recovery (MTTR) is the wrong metric for AI-era engineering teams because AI tools produce 41% more bugs and 98% more pull requests, making MTTR unable to keep up, according to CTO Evan Marshall. Marshall arg…
Figma Console MCP v1.36.0 introduces a target lock feature for parallel work, allowing AI agents to pin an active Figma file so commands do not route to the wrong file. The Model Context Protocol server gives AI assistan…
Vibe Thinking, an organization that restructured its entire operations—including product management, quality assurance, and governance—reports shipping more software than ever after six months of transformation. The comp…
Anthropic has released Claude Fable 5, the first model in the new Claude 5 family and part of a Mythos-class tier above Claude Opus. Claude Fable 5 is the most intelligent generally available model with additional safety…
A months-long effort to build "AI harnesses" for intelligence analysis found that large language models attribute genuine facts to the wrong person, cite sources that do not support their claims, interpret failed searche…
A developer reports cutting Kimi K3 costs in OpenCode by switching to the k3-256k model, which consumes half the quota of the standard K3, and by choosing the right provider such as Novita.ai. The Allegreto plan now cove…
A developer has published a generic architecture blueprint for building a persistent, always-on personal AI system that acts as a second brain for any LLM. The system is designed to be brand- and frontend-agnostic, with …
A developer built Phobos, a tiny scale-free kernel language that compiles to PTX and runs on NVIDIA GPUs, achieving 76% of cuBLAS SGEMM performance on a 2080 SUPER. The language supports tile-DAG design and was created a…
Anthropic suspended access to its Claude Fable 5 and Mythos 5 models for all customers after a US government directive citing a potential jailbreak as a national cybersecurity risk, a move Anthropic disputes as based on …
Anthropic has released Claude Fable 5, the first model in its new Claude 5 family and part of a Mythos-class tier that surpasses Claude Opus in capability. The model shares its underlying architecture with Claude Mythos …
As of August 22, 2026, a reference table covering 18 AI CLI and API surfaces shows that reasoning-effort rung names, counts, defaults, and the position of 'high' vary widely across vendors, with only Z.ai's GLM-5.3, Moon…
Autonomous agentic engineering tools have matured into a distinct category, with the Yegge ecosystem becoming its center of gravity: Gastown reached v1.0 with 15.9K stars and a Kilo-hosted cloud version, while Gas City e…
OpenSSH 10.5 was released on 2026-08-11, featuring security fixes and new features, including a fix for an ssh-agent interaction that could allow remote operations when the agent was locked. The OpenSSH team announced th…
Hermes Agent, an open-source personal AI agent from Nous Research, runs on a VPS to stay always-on, managing scheduling, memory, and task routing across a user's day. The author's postmortem emphasizes that the key to su…
The InfoQ Culture and Methods Trends Report for 2026, featuring a panel of QCon speakers and InfoQ contributors, highlights that AI adoption demands maturity frameworks to assess risk and context, and warns that organiza…
A Python test that mocks a third-party API call can pass for the wrong reason if the mock does not actually intercept the call. Developers can verify mock interception by adding `mock_get.assert_called_once()` after the …