Featured
GPT-5.6 Sol, Terra and Luna: which model is good at what?
Sol is for deep difficult work, Terra for balanced daily production, and Luna for speed and volume. Where can you use each one, and when should you choose it?
Articles
Guides for making the right AI choice.
Practical comparisons for choosing models, coding agents and reasoning settings by real task.
type
0 resultsActive filter: All
No content matches this search or filter.
DateTypeTitleReadTag
Decision guideCoding-agent permission modes: plan, auto-edit, or full access?9 min readcoding-agentDecision guideLow vs high reasoning: which setting fits each coding-agent task?9 min readreasoningAI noteCodex CLI vs Claude Code vs Gemini CLI: which coding agent fits which task?7 min readaiAI noteGitHub Copilot SDK for Java: the agent moves inside the application6 min readaiAI noteFable 5's biology safeguards: fewer false positives, same boundary6 min readaiAI noteAnthropic hires Tino Cuéllar: the governance layer of the AI race6 min readaiAI workflowHow to verify coding-agent output: a 7-step solo workflow8 min readai-agentsAI noteNew AI models in summer 2026: a short roundup8 min readaiAI newsGoogle signs the EU AI transparency code: labels are now a product decision5 min readgoogleAI newsClaude voice mode gets Opus and Sonnet5 min readanthropicAI newsChatGPT Health launches: connected data raises both usefulness and risk6 min readopenaiAI newsOpenAI Presence: enterprise agents need a control system, not just a model5 min readopenaiAI newsMeta's SAM 3 and DINOv3 cut a scientific imaging workflow from a month to 15 minutes5 min readmetaAI productGPT-Live: the real voice AI shift is listening while speaking5 min readopenaiProduct strategyMeasure AI investment by successful work, not tokens5 min readaiModel reviewClaude Sonnet 5: not the flagship, but the right default for solo builders5 min readanthropicAI workflowClaude Reflect: see what you delegate to AI, not just how often you use it5 min readanthropicSoftware securityGitHub Agentic Autofix: from security alert to validated patch5 min readgithubAI noteAgentic AI is no longer just a pitch: what Codex usage data says5 min readyapay zekaAI noteAfter the AI rush, my workflow got quieter5 min readaiAI newsAnthropic introduces Claude Tag: an AI teammate that lives in Slack4 min readanthropicAI newsGPT-5.6 may land this week: not single answers, agentic reliability6 min readopenaiAI newsGemini 3.5 Pro is still in preview: 2M context and Deep Think6 min readgoogleAI noteThe Sonnet 4.8 that never was: a leaked codename isn't a release6 min readanthropicAI newsClaude Code's Dynamic Workflows: 750k lines migrated in 11 days7 min readanthropicAI noteThe foreign national label: reaching a frontier model from Turkey6 min readyapay-zekaAI newsFable 5 pulled: a government directive three days after launch6 min readanthropicAI newsClaude Fable 5: the public face of Mythos6 min readanthropicAI newsApple WWDC 2026 preview: is Siri moving to a 1.2-trillion-parameter Gemini?5 min readappleAI noteAnthropic asked for a 'brake pedal' on its own model: what is self-improving AI?6 min readanthropicAI newsChatGPT now 'thinks' after the conversation: Dreaming V3 and the memory debate5 min readopenaiAI newsOpenAI's Codex goes everywhere: GPT-5.5 on AWS and 'Codex for every role'5 min readopenaiAI newsMicrosoft MAI-Code-1-Flash: 5 billion parameters, 10x cheaper than GPT-5.55 min readmicrosoftIndustryAnthropic files a confidential S-1: is AI's biggest IPO around the corner?6 min readanthropicAI noteChoosing a coding agent as a solo builder: a mid-2026 guide6 min readaiAI newsClaude Opus 4.8: sharper judgment, more honesty, longer autonomy5 min readanthropicAI noteMagnifica Humanitas: Notes on Pope Leo XIV's AI Encyclical6 min readaiAI newsWhat changed in Google AI Studio after I/O 2026: Build mode, Android, Workspace and Gemini 3.5 Flash7 min readgoogleAI noteThe silent AI bug: code I shipped because it "worked" but was wrong6 min readyapay zekaAI noteAI agent vs AI assistant: the line got clear in 20265 min readyapay zekaAI newsAI built into the browser: Chrome and Edge get serious5 min readyapay zekaIndustryAI product pricing is cracking: the per-token era is ending5 min readyapay zekaAI noteSmall models are eating the big-model market5 min readyapay zekaAI noteAI in 2026: the hype is over, the boring part begins6 min readyapay zekaAI newsAnthropic ships full Claude Platform on AWS — what's different from Bedrock?5 min readanthropicAI newsAI coding tool market crossed $7B — Cursor hit $60B and $2B ARR5 min readcursorAI newsGLM-5.1 — zero NVIDIA, trained on 100,000 Huawei Ascend chips4 min readzaiAI newsGPT-5.5 Instant becomes ChatGPT's new default model4 min readopenaiAI newsKimi K2.6 — vision-capable, 1 trillion parameters, open weights4 min readmoonshotAI newsWindsurf 2.0 — Agent Command Center, Spaces, and Devin integration5 min readwindsurfAI newsAnthropic leased SpaceX's Colossus 1 — and doubled Claude Code limits6 min readaiAI newsMythos and GPT-5.5-Cyber: AI is no longer for everyone5 min readaiAI noteDeepSeek V4 preview: open-source AI is heating up again4 min readaiIndustryGoogle's $40B bet on Anthropic: what it means for an independent builder4 min readaiAI noteGPT-5.5 calls itself "AI you can delegate to" — is it?5 min readaiAI productAnthropic launched Claude Design: what it means for a solo builder4 min readaiAI noteWhat I noticed working with Claude Opus 4.75 min readai