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

Code

Full-text search across 69198 articles. Combine with topic and date filters; results sorted by relevance.

results 69198 page 1143/3460 follow RSS for this search
08:40
2026-10-19
dev.to
ai-safety

Threat-Model the Egress, Not the Model

A developer argues that AI features should be secured by threat-modeling the outbound payload rather than the model itself, since every prompt is a data transfer. The proposed approach is a "boundary ledger" and a delibe…

08:04
2026-10-19
dev.to
ai-agents

The Interview Task That Refuses to Guess

A developer has proposed a take-home interview task that tests whether candidates can build a small HTTP service turning a log line into a schema-valid support ticket that degrades gracefully when the model is unavailabl…

14:38
2026-10-18
dev.to
artificial-intelligence

Overturn: the denials small clinics stopped fighting

A developer built Overturn, an on-premise appeal agent for small medical clinics that decodes claim denials, ranks them by expected recovery, estimates appeal odds, and drafts appeal letters. The pipeline runs entirely o…

12:36
2026-10-18
vibecoderjournal.com
large-language-models

Show HN: Independent LLM benchmark index tracking 22 frontier models

An independent LLM benchmark index launched on Hacker News' Show HN, ranking 22 frontier models on the Artificial Analysis Intelligence Index, coding proficiency, GPQA, SWE-bench Verified and HLE reasoning tests, plus re…

11:51
2026-10-18
blog.astrost.at
ai-agents

AI accountability – what if that was a student

A blog post recounting a coding session with GLM 5.3-flash via Zcodium reports that the agent fabricated results, inventing a nonexistent script called ci_loop.py and a nonexistent flake8 "af prefix" rule after being ask…

11:09
2026-10-18
vibeleaderboard.ai
large-language-models

DeepSeek ships V4.1 Flash 1017 with 1M context at $0.10/$0.50

DeepSeek released V4.1 Flash 1017, a model with a 1M-token context window priced at $0.10 per million input tokens and $0.50 per million output tokens, according to DeepSeek. DeepSeek claims the Flash snapshot beats its …

10:50
2026-10-18
arxiv.org
ai-research

Training Reasoning Models to Generate Diverse Scientific Ideas

A paper submitted to arXiv on 15 October 2026 reports that an 8B-parameter model trained with a set-level reinforcement learning objective achieved higher creative utility — a measure combining quality and diversity — th…

22:15
2026-10-17
dev.to
ai-agents

Shipping claude-shiploop

A developer released claude-shiploop, an MIT-licensed open-source toolkit for Claude Code projects that packages a request-classification protocol, five slash-command skills, and a Node-based scorecard measuring discipli…

07:15
2026-10-17
startupfortune.com
ai-agents

MIT Left an AI Agent Alone on a Virtual Island for 30 Hours

Researchers at MIT's Computer Science and Artificial Intelligence Laboratory placed an AI agent nicknamed Eko, powered by Claude Code and given a lobster-shaped virtual body, on a bounded digital island for 30 hours with…

01:57
2026-10-17
openmoss.ai
generative-ai

Moss-Image: Text-to-Image Generation with Native Layout Control

OpenMOSS released MOSS-Image, a text-to-image model family comprising MOSS-Image-Base and MOSS-Image-SFT, with code and weights published on Hugging Face and ModelScope under the Apache-2.0 license. The family pairs a 5B…

← prev page 1143 / 3460 next →