Category
AI Development Articles
Page 8 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 8 of 34
The newest AI Development guides and analysis
MCP promoted its Rust SDK to Tier 1 on August 21 with 67/67 server and 50/50 client conformance. No new protocol version shipped alongside it.
#mcp#model context protocol+4 more
2026-08-21
Read Article
CrewAI 1.15.17 pins SSRF checks to every redirect hop and the resolved peer IP. The same pattern can sit in any agent tool that fetches a model-supplied URL.
#crewai#ssrf+4 more
2026-08-20
Read Article
JetBrains reports 83% faster, 64% cheaper and 63% fewer tool calls for its refactoring skill. The disclosure is unusually good; the scope is one harness.
#jetbrains#rider+4 more
2026-08-20
Read Article
A free, anonymous 1M-context reasoning model appeared on OpenRouter on August 20. Nobody has claimed it, and its no-training promise is a one-off exception.
#ox-alpha#openrouter+4 more
2026-08-20
Read Article
Anthropic's browser use tool reached GA on August 19, 2026 as browser_toolset_20260801. It reads the accessibility tree; computer use reads pixels.
#browser-use#computer-use+5 more
2026-08-19
Read Article
OpenRouter's ~z-ai/glm-latest is a permanent floating router. It currently resolves to GLM-5.3 and will silently repoint when Z.ai ships its next model.
#openrouter#model-pinning+4 more
2026-08-19
Read Article
OpenAI previewed Private Safety Processing on August 19, 2026: pattern detection across related interactions for ZDR customers. Preview, not GA.
#openai#zero-data-retention+4 more
2026-08-19
Read Article
Claude Code v2.1.234 hardened the remaining pre-approval NTLM path accesses. Codex CLI 0.148.0 added Bedrock and session forking. What changed for operators.
#claude code#codex cli+5 more
2026-08-18
Read Article
GLM-5.3's direct token-metered API went live on August 18. Thinking can no longer be disabled, and the effort tiers are low, high and max only.
#glm-5.3#z.ai+5 more
2026-08-18
Read Article
Seventeen coding agents, six questions each, vendor documentation only. What the published terms say on retention and training, and which cells stayed open.
#coding-agents#data-retention+5 more
2026-08-17
Read Article
Grok 4.6 reached Cursor the day it launched. The argument that switching cost has moved to the harness, set out with its counter-evidence alongside it.
#coding-agents#model-switching+5 more
2026-08-17
Read Article
Anthropic's engineering post publishes auto-mode classifier results across three separate datasets. Why an FPR and an FNR from different sets cannot be paired.
#claude-code#auto-mode+5 more
2026-08-16
Read Article
A census of 30 models publicly described as open in 2026, with the licence read directly wherever the tag was non-standard. Full table, method and caveats.
#open-weight-models#ai-licensing+5 more
2026-08-16
Read Article
We collected 42 vendor-published benchmark rows from 9 vendors and checked what each page discloses: version, subset, harness, effort. Full table in the post.
#ai-benchmarks#vendor-claims+5 more
2026-08-16
Read Article
A vendor-published disclosure ledger reports thousands of findings across hundreds of open-source projects. What maintainers and security teams should check.
#ai-security#vulnerability-disclosure+5 more
2026-08-15
Read Article
Every vendor names its reasoning-effort settings differently and the rungs do not line up. What the ladders look like, and where thinking cannot be disabled.
#reasoning-effort#llm-configuration+5 more
2026-08-15
Read Article
DeepSeek's changelog now carries a GA entry for V4-Pro across app, web, and API, MIT-licensed 0813 weights on Hugging Face, and pricing changing August 16.
#deepseek#deepseek-v4-pro+5 more
2026-08-15
Read Article
Google's own table has Gemini 3.7 Flash winning some rows and losing others to Sonnet 5 and GPT-5.6 Terra. Every benchmark it published, read closely.
#gemini-3-7-flash#claude-sonnet-5+5 more
2026-08-14
Read Article
GLM-5.3 reuses GLM-5.2's base model, so Z.ai says every gain is post-training. Terminal-Bench 3.0 jumped 4.6 to 28.3, and weights are promised later.
#glm-5-3#z-ai+5 more
2026-08-14
Read Article
Anthropic, OpenAI and Gemini all ship schema-constrained JSON now, but their supported subsets differ enough to quietly break one shared Zod schema.
#structured-output#json-schema+5 more
2026-08-14
Read Article
OpenAI's Ultrafast tier claims up to 14x faster GPT-5.6 Sol on Cerebras hardware. It is a waitlist-gated preview with no price and no GA date.
#gpt-5-6-sol#openai+5 more
2026-08-13
Read Article
Gemini 3.7 Flash ships at $0.75/$3.75 per M through Dec 31, 2026 — but Google cut 3.6 Flash to that same intro rate, so half-price needs an asterisk.
#gemini-3-7-flash#google-deepmind+5 more
2026-08-13
Read Article
On August 12, DeepSeek's pricing page listed V4-Pro-0813 with no changelog entry and a homepage saying nothing had changed. GA was announced a day later.
#deepseek#model-versioning+5 more
2026-08-12
Read Article
xAI's Grok 4.6 keeps Grok 4.5's headline rates, but the $2/$6 tier only holds below a 200K-token prompt: cross it and the whole request reprices.
#grok-4-6#xai+5 more
2026-08-12
Read Article
Digital Applied newsletter
Deep dives on AI, marketing and development.
Practical guides and fresh insights by email. No recycled takes.