Category
AI Development Articles
Page 6 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 6 of 34
The newest AI Development guides and analysis
A fixed $200 converted into input tokens at the rate lanes seven vendors publish. Claude Opus 5 alone spans 40M to a derived 800M, a 20x range.
#ai-api-pricing#prompt-caching+5 more
2026-08-31
Read Article
A provider census of open-weight model hosting. The same model name arrives at different quantizations and context limits, with wide price and speed spreads.
#open-weight-models#inference-providers+5 more
2026-08-31
Read Article
EQ-Bench Creative Writing v3 and arena.ai do not just re-rank models for creative writing. They invert: Fable 5 is first on one board and sixth on the other.
#ai-writing-quality#llm-benchmarks+5 more
2026-08-31
Read Article
A census of what eleven coding-agent harnesses isolate by default and by flag: filesystem scope, network egress, process spawning, credential visibility.
#agent-security#sandboxing+4 more
2026-08-30
Read Article
Compare model API prices by surface, with September 9 Astra and Mercury updates and OpenRouter observations. Original rows retain their earlier source dates.
#ai-api-pricing#pricing-tracker+4 more
2026-08-30
Read Article
Compare 54 dated vendor model-limit rows plus 12 OpenRouter routes observed September 9. Keep context capacity, served context and output limits separate.
#context-window#max-output-tokens+4 more
2026-08-30
Read Article
Two 14x claims and one 35x claim landed in one month, measuring three different things. A speedup is a ratio, and the matched run is never in the headline.
#benchmark-methodology#vendor-claims+4 more
2026-08-30
Read Article
Output truncation returns HTTP 200 and valid-looking partial content. The stop-reason field is the only signal, and it is named differently on every API.
#agent-reliability#output-truncation+4 more
2026-08-29
Read Article
Anthropic says it cut 80% of Claude Code's system prompt on its own evals. An independent re-measurement says 70%. We audited our own files and cut 11%.
#context-engineering#claude-md+4 more
2026-08-29
Read Article
Thirty-eight dated changes to paid AI coding plan limits in 2026 across nine vendors. In 14 rows the vendor's framing and the effective direction disagree.
#usage-limits#ai-coding-tools+4 more
2026-08-29
Read Article
Anthropic raises Claude Code's standard weekly limits 25% above the old baseline on September 14 — a 17% cut against today, by Anthropic's own math.
#claude-code#anthropic+4 more
2026-08-29
Read Article
Default-allow's real cost is not a model mistake but a documented attack primitive. When ask-first is theatre, and why reversibility should route the call.
#agent permissions#coding agents+4 more
2026-08-29
Read Article
Eighteen AI coding tools, the instruction files each reads, precedence when several apply, and load behavior — from 27 vendor docs, retrieved Aug 30, 2026.
#ai-agent-instructions#agents-md+4 more
2026-08-29
Read Article
Active parameters, not total parameters, predict per-token cost and throughput. What the activation count tells you, and the four things it cannot tell you.
#mixture-of-experts#active-parameters+5 more
2026-08-28
Read Article
Four dated instances since June 2025 of a frontier lab restricting model access, three of them involving a coding tool. Nothing was cut off overnight.
#model-access#vendor-risk+6 more
2026-08-28
Read Article
Z.ai published GLM-5.3's 753B weights on August 28 under a bespoke licence, two days after shipping GLM-5.3-Flash under plain MIT. The clause that differs.
#glm-5-3#z-ai+5 more
2026-08-28
Read Article
OpenAI says it will wind down the contract supplying its models to Cursor, with a proposed cutoff of November 12, 2026. What BYOK does not cover.
#openai#cursor+5 more
2026-08-28
Read Article
In the 2025-26 record we checked, two labs gave a public reason before holding back open weights. What a stated delay tells a buyer, and what it does not.
#open-weights#model-releases+5 more
2026-08-28
Read Article
Clip length and resolution each collapse distinct mechanisms coverage flattens into one number. A reference for reading AI video spec sheets against the docs.
#ai video#video generation+5 more
2026-08-27
Read Article
fal says H3 Max renders five seconds of video in under three. The claim is the vendor's own, and the tracker it cites backs the quality half only in part.
#fal#minimax h3+5 more
2026-08-27
Read Article
Google's Omni 1.1 Flash chains 10-second extensions up to 40 seconds and documents 1080p and 4K as upscales. What the reported $0.03/s draft tier buys.
#gemini omni 1.1 flash#ai video generation+5 more
2026-08-27
Read Article
Text input has one unit. Image input has several conversion rules, and some vendors publish none. An input-side reference that names what it will not normalize.
#multimodal#ai-pricing+4 more
2026-08-26
Read Article
OpenRouter documents what its rankings count and what they exclude. A source-pinned inventory of what a usage chart measures, and what it cannot tell you.
#openrouter#usage-data+4 more
2026-08-26
Read Article
Z.ai named its stealth model on August 26 and shipped MIT weights the same day. What the identity actually changes for an endpoint already in production.
#glm-5-3-flash#ox-alpha+5 more
2026-08-26
Read Article
Digital Applied newsletter
Deep dives on AI, marketing and development.
Practical guides and fresh insights by email. No recycled takes.