Category
AI Development Articles
Page 15 of 34. Deep dives into AI-assisted and agentic development. Coding agents, frontier model releases, SDKs, prompting patterns, and the engineering workflows behind building production software with AI.
Page 15 of 34
The newest AI Development guides and analysis
Anthropic's study of 400K Claude Code sessions finds domain knowledge beats coding background. What the data means for hiring, agencies, and senior judgment.
#agentic-coding#anthropic-research+5 more
2026-06-20
Read Article
Three days after launch, US export controls forced Anthropic to pull Fable 5 and Mythos 5 globally. The legal mechanism, the fallout, and the new vendor risk.
#export-controls#anthropic+5 more
2026-06-20
Read Article
SpaceX is acquiring Anysphere, maker of Cursor, for $60B all-stock. We break down the deal economics, the margin trap behind it, and what changes for your team.
#spacex#cursor+5 more
2026-06-20
Read Article
ChatGPT fell to 46.4% of AI assistant users in May 2026, its first dip below 50%. What Gemini and Claude gains mean for your multi-platform GEO strategy.
#chatgpt#ai assistant market share+5 more
2026-06-19
Read Article
LLM-as-judge beats keyword filters but costs 100x more; cascades bridge the gap. A 2026 trust-and-safety guide on moderation architecture, risks, and migration.
#ai-content-moderation#trust-and-safety+6 more
2026-06-18
Read Article
Vercel launched eve, an Apache-2.0 TypeScript agent framework where every agent is a directory. What it is, how it works, and how it compares.
#vercel-eve#ai-agents+5 more
2026-06-17
Read Article
Z.ai's GLM-5.2 lands with full benchmarks and MIT open weights: #2 on Code Arena Frontend, near Opus 4.8 on agentic coding, at GLM-5.1 pricing.
#glm-5-2#zhipu-ai+6 more
2026-06-16
Read Article
Prompt caching reuses computed KV tensors so repeated prefixes cost up to 90% less, with no quality loss. The 2026 cross-provider engineering playbook.
#prompt-caching#llm-cost-optimization+6 more
2026-06-16
Read Article
Claude Fable 5 tops SWE-bench Verified at 95%, but 99 of 100 results are self-reported and the scaffold gap can exceed 28 points. How to read the numbers.
#swe-bench#ai-coding-benchmarks+6 more
2026-06-16
Read Article
Epoch AI found errors in 42% of FrontierMath problems and shipped v2 on June 12, 2026. Scores jumped, rankings held — here is what that means for model choice.
#frontiermath#ai-benchmarks+4 more
2026-06-14
Read Article
Route each request to the cheapest model that can handle it. Model routing cuts real LLM bills 40-85% with no visible quality loss. The 2026 engineering guide.
#llm-routing#ai-cost-optimization+5 more
2026-06-14
Read Article
Cohere's first open-source model is a 30B MoE that runs on a single H100, scores 33.4 on the Coding Index, and ships under Apache 2.0. Full breakdown.
#cohere#north-mini-code+5 more
2026-06-13
Read Article
DiffusionGemma is Google's first open-weight text diffusion LLM: a 26B MoE under Apache 2.0 hitting 1,100+ tokens/sec on one H100. Where it wins and loses.
#diffusiongemma#google-deepmind+5 more
2026-06-13
Read Article
Z.ai shipped GLM-5.2 to every GLM Coding Plan tier with 1M context and long-horizon coding claims. How the distribution-first launch works and how to switch.
#glm-5-2#zhipu-ai+5 more
2026-06-13
Read Article
Kimi K2.7-Code is Moonshot's new open-source coding model: +21.8% on Kimi Code Bench v2, 30% fewer reasoning tokens, plus Kimi Code CLI plans from $19/mo.
#kimi-k2-7-code#moonshot-ai+7 more
2026-06-12
Read Article
MCP hit 110M monthly SDK downloads in 16 months. The 2026 Dev Summit and July 28 stateless spec mark its shift to enterprise infrastructure.
#model-context-protocol#mcp-dev-summit+6 more
2026-06-12
Read Article
A panel of 8,128 users puts AI agent task completion at 75.3%, yet 54% still trust manual search more. Inside the per-agent variance and the 2026 trust paradox.
#AI agents#task completion+6 more
2026-06-12
Read Article
Oracle customers can soon apply Universal Credits to OpenAI models and Codex via OCI. Why this procurement-rails shift matters for regulated enterprises.
#OpenAI#Oracle+6 more
2026-06-12
Read Article
Stanford's 2026 AI Index distilled into 20 essential numbers: $581.7B in AI investment, a closing US-China gap, jagged intelligence, and what it means for you.
#Stanford AI Index#AI statistics 2026+6 more
2026-06-12
Read Article
On June 9, 2026, ChatGPT's GPT-5.5 personalization reached Free and Go tiers, drawing on past chats, files, and Gmail. What agencies must do about data policy.
#ChatGPT#GPT-5.5+6 more
2026-06-11
Read Article
Claude Code v2.1.166-2.1.169 add fallback model chains and a safe mode for clean-slate troubleshooting. A resilience guide for teams running CI agents.
#claude-code#fallback-models+6 more
2026-06-10
Read Article
Gemma 4 12B processes text, image, audio, and video with no separate encoders, fitting in ~7GB at 4-bit. A guide to running private multimodal agents locally.
#gemma-4#local-ai+6 more
2026-06-10
Read Article
Claude Fable 5 & Mythos 5 as an agentic coding model, read from the system card: the real coding benchmarks, the candid failure modes, and how to oversee it.
#claude-fable-5#claude-mythos-5+6 more
2026-06-09
Read Article
Claude Fable 5 leads the benchmarks; GPT-5.5 costs half as much and owns Codex. We compare coding, knowledge work, long context, and cost to find the fit.
#claude-fable-5#gpt-5-5+6 more
2026-06-09
Read Article
Digital Applied newsletter
Deep dives on AI, marketing and development.
Practical guides and fresh insights by email. No recycled takes.