Category
AI Development Articles
Page 10 of 35. 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 10 of 35
The newest AI Development guides and analysis
Claude Code 2.1.224 adds cross-session SendMessage, self-hosted runners on Team and Enterprise, and drops the 200-subagent cap. What ships, and what to guard.
#claude-code#self-hosted-runners+5 more
2026-08-10
Read Article
Codex CLI 0.147.0 imports Cursor-managed skills and syncs imported Claude and Cursor conversations. What is actually portable across agent harnesses now.
#codex-cli#agent-skills+5 more
2026-08-10
Read Article
Mistral's Shieldstral reads your safety policy as prompt text at inference time. A 3B Apache-2.0 guard model with a mixed, not one-sided, benchmark record.
#mistral#shieldstral+5 more
2026-08-10
Read Article
FLUX 3 Image, Grok Imagine 2.0, Midjourney, Imagen 4, Qwen-Image-3.0 and flux-2-dev: what each one actually ships versus how it gets written up.
#AI Image Models#Model Availability+4 more
2026-08-09
Read Article
Anthropic says its Fable 5 retune cut biology-related fallbacks about 85% across product surfaces. A rare published guardrail false-positive figure.
#Anthropic#AI Safety+4 more
2026-08-09
Read Article
OpenAI says it cannot rule out Critical cyber capability in Astra, an unreleased model, and published the agent controls it applied. Vendor-stated.
#OpenAI#AI Safety+4 more
2026-08-09
Read Article
UK AISI logged 19 unsanctioned agent actions across 10 of 122 cyber-range runs, with classifiers deliberately off and internet access deliberately on.
#AI Safety#Agent Security+4 more
2026-08-09
Read Article
Agent Plugins 1.0 packages skills and MCP servers in one directory format. The spec is still marked Working Draft, and vendor-specific formats keep shipping.
#agent-plugins#mcp+5 more
2026-08-08
Read Article
Block announced Buzz on 21 July 2026. Agents get a keypair and an audit trail, but channel membership is the only access control and the project is pre-1.0.
#block-buzz#self-hosted-agents+5 more
2026-08-08
Read Article
A dated ledger of what shipped in early August 2026, what was only announced, and which deadlines land before month end. Announcements stay separate.
#ai-model-releases#august-2026+5 more
2026-08-07
Read Article
OpenAI is making GPT-5.6 Luna the default for Free and Go users, with unlimited text chats due next week. Uploads, images and other tools stay capped.
#chatgpt#gpt-5-6-luna+5 more
2026-08-07
Read Article
ChatGPT's effort slider moves a developer-API control into the chat window; a Think button is announced next week. What effort changes, how vendors label it.
#reasoning-effort#chatgpt+5 more
2026-08-07
Read Article
Anthropic's August 5 beta routes every governed Claude Enterprise prompt to a security server you run, which returns an allow or deny verdict before inference.
#claude-enterprise#inference-hooks+5 more
2026-08-06
Read Article
Meta shipped Muse Code beta and Muse Spark 1.2 together on August 5, at two prices: $1.25/$4.25 standard, or $0.10/$0.20 if you contribute data.
#muse-code#muse-spark+5 more
2026-08-06
Read Article
At the time of writing there is no Wan 3.0: no Alibaba announcement, no weights, no listing. July really shipped one open-weight model and two research papers.
#wan-3-0#alibaba+5 more
2026-08-06
Read Article
GPT-5.6 Luna fell 80% and Terra 20% on July 30. Sonnet 5's scheduled $3/$15 increase was cancelled. OpenRouter list prices mix standard with batch rates.
#ai-api-pricing#gpt-5-6+5 more
2026-08-05
Read Article
BFL made FLUX 3 Video generally available on August 4 with 20-second clips, natively generated audio, and six published per-second prices from $0.06 to $0.54.
#flux-3-video#black-forest-labs+5 more
2026-08-05
Read Article
poolside trains across several agent harnesses on purpose, Cursor stitches tool-call corrections into training, Anthropic argues for holding the model fixed.
#harness-co-training#agent-training+5 more
2026-08-05
Read Article
A five-day plan to red-team AI agents with garak, promptfoo and PyRIT, mapped to the OWASP agentic categories and the MITRE ATLAS technique taxonomy.
#ai-security#red-teaming+5 more
2026-08-04
Read Article
Eight lanes of open-source AI agents mapped by licence, stars and commit activity, including which popular repos are not actually open source at all.
#open-source-ai#ai-agents+4 more
2026-08-04
Read Article
Mem0, Letta and Zep bet differently on what remembering means. A licence, architecture and benchmark comparison, including why the published scores disagree.
#agent-memory#mem0+5 more
2026-08-04
Read Article
OpenAI announced Astra with ten machine-verified math proofs and no release date, price, or model card. Reading a capability-only drop as a signal.
#openai#openai-astra+5 more
2026-08-03
Read Article
Qwen3.8-Max ships as a 2.4T-parameter MoE with 95B active and a 1M context. What the vendor benchmark table shows, and what was only promised at launch.
#qwen#alibaba+5 more
2026-08-03
Read Article
Cross-model agreement is correlated evidence, not independent confirmation. Models share training data and share errors. A reconciliation method.
#ai-development#cross-model-review+5 more
2026-08-02
Read Article
Digital Applied newsletter
Deep dives on AI, marketing and development.
Practical guides and fresh insights by email. No recycled takes.