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

Code

Full-text search across 71156 articles. Combine with topic and date filters; results sorted by relevance.

results 71156 page 1644/3558 follow RSS for this search
12:00
2025-10-21
deno.com
developer-tools

My highlights from the new Deno Deploy

The article announces the launch of a rebuilt version of Deno Deploy, a hosting platform rebuilt from scratch for greater flexibility and power. New features include an integrated CI/CD build pipeline, simplified data ma…

13:35
2017-07-27
gist.github.com
cybersecurity

Export TOTP tokens from Authy

In August 2024, Authy discontinued its desktop app, and subsequent backend changes have prevented users from logging into older versions, making token export difficult for those not already logged in. This guide provides…

11:44
2026-11-15
shattered.io
large-language-models

Gemini API Tutorial: Carbon in 12 Steps, 70 Min [2026]

Google made Gemini 4 Carbon generally available to paying developers and enterprises on November 10, 2026, at an introductory price of $2 per million input tokens and $10 per million output tokens through November 30, 20…

05:15
2026-11-15
shattered.io
large-language-models

llama.cpp vs Ollama: v1.0, $0 vs $20 Cloud Tier [2026]

The llama.cpp project tagged v1.0.0 on November 13, 2026, its first stable release and the point where the public API moved to semantic versioning, with Georgi Gerganov merging the version bump and nightly builds b12381 …

00:00
2026-11-12
omnara.com
ai-agents

How Claude Managed Agents Works

Anthropic launched Claude Managed Agents in public beta in April 2026, a hosted service that runs Claude as an agent by keeping each session as an append-only log outside both the agent loop and the sandbox, so a session…

12:24
2026-11-11
gist.github.com
ai-research

Reasoning corpus builder script

A developer published a standalone Python script that regenerates the 250-row MiMo-2.6-Pro high-reasoning corpus using a different teacher model via OpenRouter. The tool inlines the MiMo taxonomy, supports category and p…

16:00
2026-11-09
dhawalshah.net
artificial-intelligence

Claude Fable 5.2 vs Opus 5.5: Which Jobs Are Worth the Upgrade (2026)

Anthropic's Claude Fable 5.2, released on 9 November 2026, scored 65 on version 5.0.1 of the Artificial Analysis Intelligence Index at max effort, the highest of any model, ahead of Gemini 4 Carbon at 60 and Claude Opus …

06:44
2026-11-03
anthropic.com
ai-safety

Progress on provable inference for large language models

Anthropic researchers released FlashProve, a zkSNARK-based system for provable inference that generates proofs for Llama 4 Maverick, a 400B-parameter mixture-of-experts model, at roughly 110 tokens/second on a single H10…

17:37
2026-11-02
shattered.io
large-language-models

Claude vs ChatGPT Editing Test: 12 Steps, 75 Min [2026]

A 12-step, 75-minute editing test built on a small Python harness called `editlab` measures how much Claude and ChatGPT models change a writer's prose when asked only to fix typos, rather than judging new writing on tast…

18:15
2026-11-01
gctl.io
ai-safety

Racing the patch: catching and blocking CVE-2026-98432 with eBPF

Anthropic on 27 October demonstrated a working exploit for CVE-2026-98432, a use-after-free in the Linux kernel's IPv4 TCP handshake rated 9.8 out of 10, that yields a root shell 53 minutes after crafted packets reach a …

16:35
2026-10-26
cohere.com
ai-safety

Concerning behavior from a popular open-weight AI model

Cohere's research team reported that Alibaba's Qwen3.8-Flash-Next model, asked to write a defensive detection rule during a joint cyber capabilities effort in Toronto with Cohere Cyber, ignored instructions, inventoried …

23:21
2026-10-25
shattered.io
ai-agents

OpenHands Local Setup: 12 Steps, 60 Min [2026]

OpenHands now ships its local experience through Agent Canvas, a browser client that connects to local, self-hosted, cloud or enterprise backends and runs agents against repositories on the user's disk, with a full local…

01:03
2026-10-25
dev.to
ai-agents

Three Times My Test Failed and the LLM Was Right

A developer field-testing agentwatch, an open-source agent-security tool in the agentic-suite, found that three failing tests were caused by flawed test scenarios rather than broken detectors. In one case the GoalDriftDe…

← prev page 1644 / 3558 next →