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

Code

Full-text search across 71252 articles. Combine with topic and date filters; results sorted by relevance.

results 71252 page 1684/3563 follow RSS for this search
00:00
2025-09-11
jxnl.co
artificial-intelligence

Do Your Engineers Know How to Leverage AI?

Based solely on the provided text, the article explains that the key difference between engineers who successfully leverage AI and those who do not is not talent, but workflow. Engineers who treat AI as an integrated par…

09:20
2026-11-14
pgaleone.eu
ai-safety

Backdooring LLMs – Do you trust your AI provider?

A developer writing under the handle galeone published a reproducible repository (github.com/galeone/llm-poison) showing that Qwen3-8B can be backdoored with two QLoRA fine-tuning passes so that a single innocuous questi…

20:47
2026-11-13
research.google
artificial-intelligence

Advancing science & engineering with Antigravity’s /teamwork

Google Research reported on November 13, 2026 that its Antigravity /teamwork multi-agent system, built on the Gemini 4 Argon, Gemini 4 Carbon and Gemini 4 Hydrogen models, produced new results on open problems in informa…

00:00
2026-11-13
munderdiffl.in
artificial-intelligence

llama.cpp 1.0: What Changed and What to Check Before Upgrading

Llama.cpp 1.0, released on GitHub at 10:20 UTC on 13 Nov 2026 by ggml-org, removes the deprecated public API — including llama_set_warmup, 35 deprecated functions, defrag_thold and the --defrag-thold flag in pull request…

00:00
2026-11-12
blog.localstack.cloud
ai-agents

Agentic AI Security Starts Before Production

A September 2026 Dimensional Research survey of more than 300 developers and engineering managers at companies with over 1,000 employees, conducted for LocalStack, found that 79% of respondents said AI agents have access…

23:36
2026-11-11
fromtheterminal.substack.com
ai-agents

Proofs Got Cheap. Deciding What to Prove Didn't.

A research team used a multi-agent framework to produce machine-checked Lean proofs of the Signal protocol's security properties down to its shipped implementation, generating over six million lines of Lean in four weeks…

00:00
2026-11-11
docs.polytoken.dev
ai-tools

Polytoken 0.9.8

Polytoken released version 0.9.8, adding the Claude Fable 5.2 model with reasoning-effort selection and fast mode, along with fixes to incorrect model reasoning options and clearer configuration diagnostics for vision mo…

18:35
2026-11-10
faylee.app
developer-tools

Stop sending developers useless bug reports

Faylee launched a bug-reporting tool that captures a user's screen, console, network requests and click steps into a single shareable link, which the company says cuts time-to-close from a usual 4 days to 3 hours and fol…

16:03
2026-11-10
deepmind.google
artificial-intelligence

Gemini 4 Carbon is now available

Google released Gemini 4 Carbon to developers, enterprises, scientists and consumers, following a two-week early release to cybersecurity defenders through its Fairwind Program. Google said Carbon ranks #1 on CursorBench…

03:20
2026-11-10
llmleaderboard.com
large-language-models

Notes on Fable 5.2

Anthropic's Claude Fable 5.2 ranks #1 on the seven-benchmark Agent Index with a score of 89.6/100, ahead of Fable 5.1 at 83.4 and GPT-6 Astra at 86.2, while costing 20% less per token, according to the analysis. On Front…

00:00
2026-11-10
munderdiffl.in
large-language-models

Claude Fable 5.2: price, fast mode, Mythos 5.2 and when to pick it

Anthropic released Claude Fable 5.2 on 9 Nov 2026 at $8 per million input tokens and $40 per million output tokens, down from Fable 5.1's $10 and $50, according to the company's announcement. Anthropic says Fable 5.2 and…

00:00
2026-11-10
explainx.ai
large-language-models

Claude Fable 5.2 vs Opus 5.5: Benchmarks, Cost and When to Switch

Anthropic's November 9, 2026 release of Claude Fable 5.2 beats Claude Opus 5.5 on 11 of the 12 benchmarks in Anthropic's own comparison table, including a 41.3% vs 21.3% lead on the Remote Labor Index and 64.9% vs 39.4% …

22:59
2026-11-09
github.com
developer-tools

Exact – a new cross platform UI framework by the Expo team

The Expo team released Exact, a pre-1.0 cross-platform application runtime that compiles interfaces written in its declarative Contract language into native apps for web, macOS, iOS, and Linux, with no webview or JavaScr…

12:24
2026-11-06
shattered.io
ai-agents

LangChain vs LangGraph: $0 Core, $39 Plus [2026]

LangChain's standard create_agent API is now built on LangGraph, so developers no longer choose between the two libraries but instead pick which layer to write against, according to a November 3 comparison from Garage La…

05:44
2026-11-05
dev.to
ai-agents

Agent instructions that actually change behaviour

A developer has published a practical guide to writing agent instruction files that measurably change behavior, centered on a five-line rule in a global CLAUDE.md that assigns subagent models by task difficulty (haiku fo…

← prev page 1684 / 3563 next →