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

Code

Full-text search across 69514 articles. Combine with topic and date filters; results sorted by relevance.

results 69514 page 1239/3476 follow RSS for this search
15:00
2026-10-27
developer.nvidia.com
ai-infrastructure

3 Ways to Boost MoE Inference on NVIDIA DGX Spark

Swapping the FlashInfer MXFP4 MoE backend for the Humming kernel library cut time per output token from 27.71 ms to 25.35 ms and raised decode throughput from 36.09 to 39.45 tokens per second, a 9.3% gain, in a batch-siz…

14:00
2026-10-27
patrickmccanna.net
ai-agents

Prompt Patterns That Compound

A builder who writes prompts for Claude Code and hands them to agents that run unsupervised for hours reports that stacking small prompt patterns across an agent's build-measure-improve loop produces compounding producti…

07:31
2026-10-27
dev.to
artificial-intelligence

PHANTOM Terminal: Something Is Still Running 👻

Developer Varun-666 built PHANTOM Terminal, a local-first, AI-powered "haunted terminal" web app that turns user-supplied text fragments into eerie transmissions using an open-weight model served through Ollama. The proj…

07:10
2026-10-27
chele.bi
ai-agents

Stop Explaining Yourself to AI

A tutorial episode argues that AI chat memory — including ChatGPT's cross-chat and project context, Claude's per-conversation and per-project memory, and on-disk memory in Claude Code and Codex — is insufficient because …

01:15
2026-10-27
driftwatch.et
ai-infrastructure

Cloudflare: Response field result removed

Cloudflare removed the result field from responses to GET /accounts/{account_id}/ai-gateway/gateways, so reads of that field now return undefined and fail wherever the value is used rather than at the call site. The chan…

00:00
2026-10-27
vercel.com
ai-agents

Vercel Agent sessions now cost 67% less

Vercel reported that Vercel Agent sessions in the dashboard and Slack now cost 67% less on average after the company rebuilt how Agent manages context, reducing tokens per session and improving prompt-cache reuse. The ch…

22:56
2026-10-26
docspring.com
developer-tools

How to Upgrade PostgreSQL Without Downtime Using PgBouncer

DocSpring released db-cutover, an open-source Python CLI that upgrades PostgreSQL databases with no downtime by running a second database on the target version, copying data via logical replication, and using PgBouncer t…

19:41
2026-10-26
driftwatch.et
ai-tools

Cloudflare: messages changed type

Cloudflare's POST /accounts/{account_id}/ai/websearch endpoint now returns an object where the messages[] field previously returned null, according to the company's published API specification. Clients reading messages[]…

18:14
2026-10-26
driftwatch.et
artificial-intelligence

OpenAI: value can now return "gpt-6.1-terra"

OpenAI added "gpt-6.1-terra" as a new value to its BetaModelIdsShared schema, which the change notice says is reachable from 4 operations and affects code reading those objects across 5 OpenAI operations. The addition br…

← prev page 1239 / 3476 next →