ChatGPT Guide: Prompts, Tips & Advanced Techniques

You don't have to ask for "lead with the conclusion" or "keep it in plain English" every time: write it once in the instruction field that automatically applies to every conversation. That field is "Custom Instructions" in ChatGPT, "Instructions for Claude" in Claude and "Instructions for Gemini" in Gemini, but the three differ in what it is called, where it lives and how much you can write. ChatGPT allows 1,500 characters on Free and Go and 5,000 on Plus and higher plans (raised in July 2026), while Claude and Gemini don't publish a limit. This article checks the location and limit of each against the companies' official help, then uses Anthropic's official prompting guide to show how to write instructions that work, with an example. It also turns the situations the official help pages say instructions don't take effect, such as inside projects, inside Gems, in temporary chats and on company accounts, into a checklist.

OpenAI released GPT-6 Astra on September 3, 2026. The API is generally available with no gating, the model ID is gpt-6-astra, the context window is 1,050,000 tokens, pricing is $10 in / $50 out per million tokens, and the knowledge cutoff is April 30, 2026. But "it launched" and "your plan can use it" are two different things: on ChatGPT Plus it does not appear in the regular chat interface, and the way in is ChatGPT Work and Codex. This article covers availability by plan, how to think about pricing when a 2x unit price can still be cheaper per task, the benchmarks OpenAI actually named, the cybersecurity capability that reached "Critical" under the Preparedness Framework for the first time and the line OpenAI drew around it, the four things that break when you migrate (sampling parameters removed, Responses API, no none reasoning effort, the renamed cache setting), and a comparison with Claude Opus 5, Fable 5.1, and Gemini 3.8 Flash — restricted throughout to what could be confirmed against primary sources. It also shows, with each publisher named, how the same DeepSWE v1.1 gives Claude Opus 5 73.7% in the OpenAI table but 68.8% in the Anthropic announcement.

ChatGPT Work is the "AI agent for work" that OpenAI announced on July 9, 2026 alongside GPT-5.6. Unlike a regular chat that just answers, it gathers context from your connected apps and files to build finished deliverables — documents, spreadsheets, slides, and even web apps. It launched on GPT-5.6, then GPT-6 Astra (September 3) and GPT-6 Sol and Luna (September 22) were added, so paid plans can pick anything from the top-tier model to balanced and low-cost ones in Work to fit the task. Astra is limited on Plus and Business Standard, while Pro and Business Premium can spend their full allowance on it (OpenAI Help, as of September 25, 2026). Work differs from regular chat in its allowance (shared with Codex) and in which models you can pick; Codex offers the desktop app, CLI, IDE, and Cloud tasks on web and phone, while Work runs on web, phone, and desktop. OpenAI's wording on Free and Go is inconsistent. Built on OpenAI's own announcement, Help Center, and release notes, this article lays out what ChatGPT Work is, how it differs from regular ChatGPT and Codex, which models each plan can use, and which apps it connects to — with dates and confidence labels.

On July 8, 2026, OpenAI released "GPT-Live," a new model that overhauls ChatGPT's voice worldwide. Its headline feature is a full-duplex architecture that "listens and speaks at the same time": it returns backchannels (mhmm/yeah) while you're still talking, absorbs interruptions mid-sentence, and doesn't mistake your thinking silences for "you're done" and cut you off — a fundamental break from the turn-based (half-duplex) Advanced Voice Mode. GPT-Live handles conversational responsiveness, and when web search or deep reasoning is needed it delegates to a model behind the scenes so the conversation never stalls (GPT-5.5 at launch; GPT-5.6 or GPT-6 Astra since September 9, 2026). At launch Free defaulted to GPT-Live-1 mini and Go/Plus/Pro to GPT-Live-1; since September 9, Go uses mini as well. In human evaluations it was clearly preferred over Advanced Voice Mode. This article explains, based on the official announcement, what GPT-Live is, how it differs from the old mode, how it works, the two models and plans, its main advances, and the limitations worth being honest about (no video or screen sharing, full multilingual parity not yet reached), plus the API that became generally available on September 10, 2026, and how it differs from GPT-Realtime-2.1.

An in-depth comparison of GPT-5.6 Sol, OpenAI's flagship as of July 2026, and Google Gemini. Unlike the earlier battles against Claude, their strengths barely overlap: Sol dominates agentic and terminal coding (Terminal-Bench 2.1 88.8% vs 70.7%, SWE-bench Pro 64.6% vs 54.2%, both from OpenAI's evaluation table), while Gemini counters with native multimodality (voice and video) and a unit price about 40% of Sol's ($2/$12 up to 200K tokens vs $5/$30). There is also an important "timing trap": Google's true challenger, Gemini 3.5 Pro, was not yet released as of this writing (GA had been planned for mid-July 2026, and it was still unavailable on September 22), so the comparison target is Gemini 3.1 Pro (February 2026, still a preview in the API). This article lays out a spec cheat sheet, coding/reasoning/multimodal benchmarks, the multimodal gap that is Gemini's home turf, real cost (Gemini about 40% of Sol; on the GPT side Terra matches Gemini), a strengths-and-weaknesses map, and use-case-based selection, grounded in official announcements and independent benchmarks. For the successor, GPT-6 Astra (September 2026), see the note at the top.

Arriving July 9, just two and a half months after April 2026's GPT-5.5, GPT-5.6 is not merely a performance bump — the biggest change is the reorganization from a single flagship into a three-model lineup: Luna/Terra/Sol. What matters most to many GPT-5.5 users is that the mid-tier Terra delivers GPT-5.5-class quality at a far lower price: it launched at half price, and the July 30, 2026 price cut took it to 40% of GPT-5.5's unit price ($2/$12). For those wanting more performance there is the top-tier Sol (same $5/$30, with SWE-Bench Pro rising 58.6→64.6% per OpenAI); for those wanting lower costs there is Terra. This article lays out, based on official announcements and independent analysis, what the three-model shift means, a spec-at-a-glance table, Terra's price-to-performance, generational benchmark gains (same-metric SWE-Bench Pro +6pt; TerminalBench versions differ between announcements, so compare within one table; general-reasoning gains are small), 5.6's new features (Programmatic Tool Calling, max effort, ChatGPT Work, GPT-Live, GitHub Copilot support), real cost (roughly $1,100→$440 for 100M input/20M output a month), and which model you should migrate to (cut the bill by 60% with Terra, then move only performance-critical work to Sol).

An in-depth comparison of OpenAI's then-flagship GPT-5.6 Sol (July 9) and Claude Fable 5 (June 9), which Anthropic positioned at launch as "the most powerful model it has ever made generally available." Where the Opus 4.8 matchup was a head-to-head in the same price tier, this one turns on a cost-versus-capability trade-off: "the half-price all-rounder Sol ($5/$30)" against "the twice-as-expensive but top-tier Fable 5 ($10/$50)." On production-grade coding's SWE-Bench Pro, Fable 5's 80.0% pulls more than 15 points ahead of Sol's 64.6% in OpenAI's table, which lists both — a gap wider than in the Opus 4.8 matchup. Fable 5 also stays focused across millions of tokens and, per Anthropic, works autonomously for longer than any previous Claude, with Stripe finishing a 50-million-line Ruby migration in a single day as its home-turf "follow-through." Sol, meanwhile, leads on terminal operation (TerminalBench 2.1 88.8% vs Fable 83.1%), Agents' Last Exam (53.6 vs 40.5), and Coding Agent Index (80 vs 77.2), plus best value with half the price and +54% token efficiency. This article covers the spec cheat sheet, benchmark details, the "undisclosed-benchmark problem" (metrics missing from OpenAI's table, and OpenAI questioning SWE-bench Pro itself), long-running autonomy, real cost (viewed per completed task), a strengths-and-weaknesses map, and how to choose by use case — all grounded in official and independent benchmarks.

An in-depth comparison of the two AI-coding giants as of July 2026, Claude Opus 4.8 (May 28) and GPT-5.6's top-tier Sol (July 9). Their strengths are almost opposite: Sol leads in terminal operation and overall agentic capability (TerminalBench 2.1 88.8% vs Opus 78.9%, Agents' Last Exam 53.6, Coding Agent Index 80), while Opus 4.8 leads in production-grade coding (SWE-bench Pro 69.2% vs Sol 64.6%), and foregrounds honesty (about 4x less likely to let flaws in its own code slip by; fails to flag important failures only 3.7% of the time). GPQA Diamond and FrontierMath, once reported as undisclosed, are in OpenAI's evaluation table with Sol ahead (as it is on GraphWalks 1M), and on SWE-bench Pro even OpenAI's own table puts Opus ahead, so in coding's heartland Opus has the edge. We cover the spec table, benchmark details, the undisclosed-benchmark problem, real cost ($25 vs $30 unit price vs +54% token efficiency), a strengths/weaknesses map, use-case picks, and a dual-vendor strategy.

OpenAI made GPT-5.6 generally available on July 9, 2026, replacing the old "standard + Pro" structure with a three-model lineup: Luna (fast, low-cost, $0.20/$1.20), Terra (balanced, $2/$12, GPT-5.5-class at 40% of Sol's unit price), and Sol (flagship, $5/$30) — prices as revised on July 30, 2026. Sol takes first place on Agents' Last Exam (53.6) and the Coding Agent Index (80), and its 88.8% on TerminalBench 2.1 beats Claude Fable 5 (83.1%) — yet on production-grade SWE-Bench Pro, Claude Fable 5 leads decisively at 80.0% against Sol's 64.6%. This article covers the differences between the three models, pricing, benchmarks, new features (Programmatic Tool Calling, ChatGPT Work, the full-duplex GPT-Live voice model), availability by ChatGPT plan, a comparison with Claude (Fable 5 / Opus 4.8), and how to choose by use case — all grounded in OpenAI's official announcement and independent benchmarks.

AI can be a know-it-all friend that keeps up with a child's "why?" and a storyteller before bed — but with kids, the safety setup matters before the fun. This article sets five safety promises first (① an adult operates and checks ② check age limits ③ enter no personal info ④ teach that AI can be wrong ⑤ set the tone and time), then gives a table of age rules checked against each company's terms (ChatGPT 13+ with a parent's permission under 18, Copilot 13+, Claude 18+, and Gemini for under-13s via Family Link where a parent allows it and it's offered), step-by-step parent settings (ChatGPT parental controls, Google Family Link, Microsoft Family Safety, and temporary chats on an adult account), and common mistakes. Then come 10 copy-paste activities: stories and words (a bedtime story where your child is the hero, a kids-decide story, a calm bedtime tale), learning and curiosity (a know-it-all professor, an animal & dinosaur quiz, greetings in other languages), and making and expression (drawing an imagined creature, coloring pages, crafts, feelings role-play). Tips by age, what parents should know, and an FAQ.

The most addictive way to play with AI is a text adventure with AI as your game master (GM): you declare an action, the AI describes the scene and the story branches, and it even handles wild actions outside the given choices. This article walks through how to build one from start to finish with copy-paste prompts: a starter prompt you just paste, the 5 parts that decide the fun (① setting ② tone ③ rules ④ state-tracking ⑤ pacing), genre presets (fantasy adventure, horror escape, mystery investigation, sci-fi survival, cozy slice-of-life), next-level tricks (dice for luck, stats and levels, save & resume), how to fix it when it goes wrong (too soft / runs on its own / on rails / forgets the state), and tips for long play. No programming, works on free ChatGPT, Claude, or Gemini. With cautions and an FAQ — the deep-dive companion to item ⑦ of "15 fun ways to use AI."

Stuck on "what am I even supposed to ask an AI?" This gives you 30 ready-to-paste prompts that get a fun reply back the moment you paste them. Six genres of five: get to know yourself (hidden strengths, shared values, which animal you are), spark ideas and what-ifs (unexpected uses for an everyday object, if gravity were halved, inventing a holiday), explanations that click (quantum mechanics for a 5-year-old, compound interest in three metaphors, the internet as pizza delivery), wordplay (rewrite in 10 styles, a two-sentence micro-story, epithets, palindromes), role-play and advice (a tough life coach, a sage who invents proverbs, a letter from your future self, a baffled alien), and useful-but-fun (turn an excuse into a maxim, five levels of saying no, fix a bland message, dramatic menu names, a fun detour in your to-do). Works on free ChatGPT, Claude, or Gemini. Includes tips (stack "more," add role and constraints, switch AIs), cautions, and a link to the sister article "15 fun ways to use AI."