grep -r "Code" /news · home›search
grep -rli "Code" /news

Code

Full-text search across 70332 articles. Combine with topic and date filters; results sorted by relevance.

results 70332 page 1382/3517 follow RSS for this search
20:38
2026-10-27
dev.to
ai-agents

Your AI Agent Graph Compiles. That Doesn't Mean It's Correct.

A developer demonstrated that TypeScript's type system cannot catch structural bugs in multi-agent workflow graphs, using a LangGraph contract-processing example where a fast-track route reaches a publish node without ev…

20:00
2026-10-27
tech.slashdot.org
artificial-intelligence

Google's Genie 4 World Model Adds Audio, More Realistic Worlds

Google DeepMind released Genie 4, its newest world model, in research preview on Tuesday, generating more photorealistic interactive worlds with real-time audio including music, ambient noise and interactive dialogue. Ge…

19:53
2026-10-27
osintsights.com
ai-agents

AI Agent Exposes Severe Bugs in Industrial Control Software

An autonomous AI agent named Cipher uncovered four severe bugs in the industrial control software EPICS Base in three hours and 49 minutes without human intervention, prompting the US Cybersecurity and Infrastructure Sec…

18:51
2026-10-27
usejog.com
ai-agents

Show HN: Jog – GitHub runners for 80% less

Jog launched a GitHub Actions runner service that it says costs 80% less than GitHub's hosted runners and 70% less than Blacksmith and WarpBuild, with 1,000 CI minutes priced at $1.20 versus $6 on GitHub. Jog runs jobs o…

18:03
2026-10-27
aiflash.com
artificial-intelligence

Study finds AI models overuse patterns linked to reading difficulty

Researchers from New York University and the University of Texas at Austin analyzed language from 14 AI models across chat, coding and essay settings, including 980 model-written essays, and found the models' outputs ove…

17:18
2026-10-27
search2o.com
ai-agents

Show HN: Search2o Simplifies AI Agents

Search2o released an agent server that lets clients discover and run agents through two calls, search() and execAgent(), installed via pip install search2o. The company said the agent server is stateless and can run in a…

17:03
2026-10-27
dev.to
ai-agents

Your subagent chain is paraphrasing your safety rules

An analysis of OpenAI's October 20 report on its internal coding agents highlights how safety instructions degrade across subagent handoffs: an explicit rule against disabling monitoring softened to "preserve monitoring …

16:47
2026-10-27
playplanet.dev
ai-tools

Show HN: I built a Lovable Alternative that runs in the browser

A team launched playplanet.dev, a browser-based alternative to Lovable that builds and runs full-stack apps entirely client-side on a Linux-like system compiled to WebAssembly with a runtime on top, supporting Astro, Rea…

16:24
2026-10-27
globatics.live
ai-search

Watch your visitors live on a globe

Globatics unveiled a real-time analytics dashboard that plots each current visitor as a dot on a globe, generates anonymous names and glyphs for visitors, and treats ChatGPT, Perplexity, Claude and Gemini as a first-clas…

15:00
2026-10-27
hindsight.vectorize.io
ai-agents

What's New in Hindsight Cloud: The API Is a Promise Now

Vectorize announced that Hindsight Cloud reached version 1.0, making its API stable and backward-compatible so existing code, SDKs and MCP setups keep working unchanged. Most of Hindsight Cloud now runs on Memlake, a Rus…

14:55
2026-10-27
cryptobriefing.com
artificial-intelligence

Axiom’s AI agents formalize a 15,000-page math proof in 24 days

Axiom Math announced on October 26, 2026 that its AxiomProver multi-agent system completed the first full computer-checked formalization of the Classification of Finite Simple Groups, translating the roughly 15,000-page …

13:40
2026-10-27
dev.to
ai-tools

Find Fragile Cases With a Cross-Model Pass Matrix

A developer has published a lightweight, standard-library-only harness that runs the same golden eval cases against multiple models and records a per-case pass vector rather than a single aggregate score, making cross-mo…

12:57
2026-10-27
marktechpost.com
artificial-intelligence

Mirendil Launches Fern 0.1, Its First Model, With 10M-Token Context

Mirendil released Fern 0.1, its first model, pretrained from scratch with a 10M-token context window aimed at agentic AI R&D work. Fern 0.1 scores 100% on RULER single needle at 10M tokens but trails frontier models on a…

12:31
2026-10-27
dev.to
ai-infrastructure

Free Workers Don't Ship Free Disk: Cap Artifact Retention First

A developer documented a batch-processing incident in which 4,000 jobs writing roughly 2 MB of artifacts each filled a worker's disk after three days, causing write failures and requeued jobs that re-spent tokens on alre…

← prev page 1382 / 3517 next →