by admin | Jul 17, 2026 | AI Tools
Did you open ChatGPT this week and spot model names like Sol, Terra, or Luna? You are not imagining things. On July 9, 2026, OpenAI released GPT-5.6, a new family of three models, and the naming system changed along with it. If the announcement felt like it was written for developers and investors, this post is for you.
Here is a simple explanation of what GPT-5.6 actually is, what the three names mean, which model you get on your plan, and what any of this means for your daily work and study.
What is GPT-5.6?
GPT-5.6 is the newest generation of the AI models that power ChatGPT. According to OpenAI’s official announcement, it launched on July 9, 2026 across ChatGPT, Codex, and the OpenAI API, with a global rollout in the following days.
The headline is not one giant model. It is a family of three: Sol, the flagship; Terra, a balanced model for everyday work; and Luna, the fastest and most affordable one. OpenAI says the whole family was trained to get more useful work out of every token, which in plain language means better answers with less computing, and therefore lower cost. If the word token is new to you, our short guide on what a token in AI means explains it in two minutes.
Sol, Terra, and Luna: what the names mean
The names are Latin for sun, earth, and moon, and they work like sizes rather than versions. The number tells you the generation, and the name tells you the capability tier:
- Sol is the most capable model, built for the hardest tasks.
- Terra is the middle option, tuned for everyday work at a lower cost.
- Luna is the smallest and cheapest, made for speed and volume.
OpenAI says these tiers are here to stay, so future generations should keep the same three names. That is genuinely helpful. Anyone who has tried to explain the difference between older model names to a colleague knows how confusing AI naming has been. If you want a refresher on how these systems work under the hood, see our beginner guide to large language models.
Which model do you get on your plan?
This is the part most readers care about. Based on the official availability notes:
- In ChatGPT, paid users on Plus, Pro, Business, and Enterprise plans get GPT-5.6 Sol. Pro and Enterprise users can also pick Sol Pro for the highest quality on complex tasks.
- In ChatGPT Work and Codex, free and Go users get GPT-5.6 Terra, while paid plans can choose between Sol, Terra, and Luna and set how much effort the model puts in.
- Developers can use all three models through the API.
The interesting detail is that Terra, the model free users get in ChatGPT Work, performs at a level competitive with GPT-5.5, which was the flagship generation before this one. Free access to near flagship quality is a quiet but real win for students and anyone learning AI on a budget.
What is actually new for everyday users?
Beyond benchmark numbers, a few changes matter in practice. OpenAI says GPT-5.6 is noticeably better at producing finished, usable work: editable presentations, well formatted documents, and spreadsheets that follow a template you give it. It is also better at design, so interfaces and visual material it creates need less cleanup. Microsoft clearly agrees, since GPT-5.6 is now the preferred model in Microsoft 365 Copilot.
There is also a new high effort setting called ultra, which runs four AI agents in parallel on one task. It is aimed at heavy professional work and sits behind the higher paid plans, so most casual users will not see it. The takeaway is the direction: AI tools are moving from answering questions toward completing whole pieces of work, something OpenAI leans into with its ChatGPT Work pitch.
From my own experience running websites and testing online tools, launch week claims always deserve a calm head. The demos are impressive, but the honest test is your own work. Give the new model one real task you do every week and compare the result with what you got before.
What about safety?
GPT-5.6 is stronger at cybersecurity tasks than any previous OpenAI model, and that cuts both ways. OpenAI says it shipped its most robust safeguards so far, with layered checks and a system that blocks roughly ten times more potentially harmful activity than before. Its most sensitive security capabilities are reserved for verified professionals through a trusted access program.
For normal users, the practical effect is small. You might occasionally see a refusal on a harmless technical question, and OpenAI offers a retry on a lower capability model when that happens. Working around cybersecurity myself, I would rather see a cautious default than an open door.
Tip: do not pay for the biggest model by default. Pick one weekly task, run it on the model your plan already includes, and only upgrade if the result genuinely falls short.
What this means for you
For most people, GPT-5.6 means the free and cheap tiers of AI just got better, the names finally make sense, and the gap between a chat answer and a finished document keeps shrinking. Prices for builders dropped too, with the smallest model costing one dollar per million input tokens, which keeps pushing capable AI into more of the apps you already use.
It also sharpens the competition. If you are deciding which assistant fits your work, our comparison of ChatGPT, Gemini, and Claude walks through the differences, and our guide to how AI memory works explains what these tools remember about you across chats.
Common questions
Is GPT-5.6 free to use?
Partly. Free and Go users get GPT-5.6 Terra in ChatGPT Work and Codex, which OpenAI says performs at a level competitive with the previous flagship generation. The top model, Sol, needs a paid plan.
What do Sol, Terra, and Luna mean?
They are capability tiers named after the sun, earth, and moon. Sol is the most powerful, Terra is the balanced middle option, and Luna is the fastest and cheapest. The number, 5.6, is the generation.
Is GPT-5.6 better than GPT-5.5?
On OpenAI’s published evaluations, yes, across coding, knowledge work, and science, and it usually gets there faster and with fewer tokens. As always, benchmark wins do not remove the need to check important facts in anything an AI writes for you.
Final takeaway
GPT-5.6 is less about one dramatic breakthrough and more about better results for less money, with clearer names on the box. Try the model your plan already gives you on a real task this week, keep your usual habit of checking its output, and you will get most of the benefit without spending anything extra.
by admin | Jul 16, 2026 | Research & Productivity
Picture this: you ask an AI tool to help with your literature review, and it hands you a perfectly formatted reference, correct author names, a real-sounding journal, a plausible year. You paste it straight into your bibliography. There’s just one problem. That paper doesn’t exist.
This isn’t a rare glitch anymore. It’s become common enough that major journals, publishers, and research-integrity teams are now treating it as one of the biggest quiet risks in academic writing today. If you use AI for research, essays, or a thesis, this is worth five minutes of your time.
What is a hallucinated citation?
A hallucinated citation is a reference that an AI tool generates that looks completely real but doesn’t actually exist, or that misattributes real findings to the wrong paper. Researchers studying this problem call the worst examples “Frankenstein” citations, because they stitch together fragments of genuine papers (a real author, a real-sounding title, a real journal name) into something that was never actually published.
The dangerous part is that these fake references rarely look fake. They’re usually formatted correctly, attributed to real researchers, and dated plausibly. Unless you actually go and check, there’s often no obvious red flag.
How big is this problem, really?
Bigger than most people realize, and it’s growing fast. A Nature news feature published in April 2026 reported that tens of thousands of papers published in 2025 may contain invalid, AI-generated references.
A separate analysis is even more specific about the scale. Researchers led by Maxim Topaz at Columbia University audited nearly 2.5 million PubMed-indexed papers and published their findings as a letter to The Lancet in May 2026, reported in detail by Retraction Watch. They found that about 1 in every 277 papers published in the first seven weeks of 2026 referenced a paper that doesn’t exist. That’s a sharp jump from 1 in 458 in 2025, and 1 in 2,828 back in 2023, a roughly 12-fold increase in fabricated citations in just two years. The researchers traced the sharpest rise to mid-2024, right around when AI writing tools became widely used.
One more detail worth knowing if you’re writing any kind of review paper: the study found review articles had a fabrication rate 57% higher than other paper types, likely because they cite so many sources at once.
Why do AI tools make up references in the first place?
General-purpose AI chatbots like ChatGPT, Gemini, or Claude are built to predict the next most plausible piece of text, not to look things up in a verified database by default. When you ask one to “give me three sources on X,” it generates something that fits the pattern of a real citation, without necessarily checking whether that exact paper exists. It’s the same underlying issue behind AI giving wrong factual answers generally, which we cover in more depth in our guide to why AI sometimes gives wrong answers.
Researcher Maxim Topaz, who led the Lancet analysis, made an important point in his interview with Retraction Watch: most of the cases his team found weren’t researchers deliberately faking sources. 91% of the flagged papers had only one or two fabricated references, which he said are “likely honest mistakes by authors who used AI tools without verifying the output.” In other words, this usually isn’t dishonesty. It’s trust placed in a tool that was never designed to guarantee factual citations.
How to check every AI-generated citation
The good news is that verifying a citation only takes a minute or two once it’s a habit. Here’s a simple process:
- Search the exact paper title in quotation marks on Google Scholar or PubMed. If nothing comes up, that’s your first warning sign.
- Check for a DOI, and paste it into Crossref’s search tool to confirm it resolves to a real, matching paper.
- Open the actual source. Don’t just trust that the AI’s summary of a paper matches what the paper really says, skim the abstract yourself.
- Be extra careful with review articles and papers that cite many sources at once, since that’s exactly where this analysis found the highest fabrication rate.
Quick tip: if an AI tool gives you a citation you can’t verify within two minutes of searching, treat it as fake until proven otherwise, not the other way around.
From my own experience working on websites and digital tools, this is really the same instinct as checking a suspicious link before you click it. You don’t assume something is safe by default, you look for confirmation first. Citations deserve the same habit.
Tools that reduce this risk
Not all AI research tools carry the same risk. Some are built specifically to ground their answers in real, searchable sources rather than generating text freely. If you’re doing a literature review, our step-by-step guide to literature reviews with AI covers tools like Elicit and Semantic Scholar, which pull directly from real paper databases and show you the actual source, rather than describing one from memory. Similarly, our guide to AI tools for thesis writing and our walkthrough of summarizing research papers with AI both lean on tools that link back to the original document, so you can check the source yourself in one click.
Free citation managers like Zotero also help here, not because they use AI themselves, but because they store the actual paper alongside the reference, making it easy to double-check what you’re citing before you submit anything.
What this means if you’re writing a thesis, paper, or report
If you’re a student or researcher using AI to speed up your work, this isn’t a reason to stop. AI is genuinely useful for finding starting points, summarizing dense papers, and organizing your reading list, our beginner’s guide to AI covers the basics if you’re still getting comfortable with these tools. The real takeaway is simpler: treat every AI-generated citation as a draft that needs verifying, not a finished fact. That one habit is the difference between using AI well and ending up in a retraction story.
Common Questions
Can AI research tools like NotebookLM or Elicit still invent citations?
They’re much less likely to, because they’re designed to ground answers in the specific documents or database you give them rather than generating references from general knowledge. But no tool is risk-free, so it’s still worth spot-checking anything that goes into a formal paper.
Is using a fake AI-generated citation considered academic misconduct?
Opinions among researchers and publishers differ, and it depends on intent and how central the citation is to your argument. Most experts agree it’s treated far more seriously if you didn’t bother to check the source at all, so verifying every reference protects you either way.
How can I quickly tell if a citation is fake?
Search the exact title in quotation marks on Google Scholar or PubMed, and check the DOI on Crossref. If the paper doesn’t turn up, or the DOI doesn’t resolve to a matching title, treat it as unverified until you find it yourself.
Final takeaway
AI can genuinely speed up research, but it can also hand you a citation that looks completely real and isn’t. The fix isn’t complicated: search the title, check the DOI, and open the actual source before it goes anywhere near your bibliography. That one habit keeps AI a useful research assistant instead of a liability.
by admin | Jul 15, 2026 | Future Jobs
You have probably seen the headlines by now: AI is destroying jobs. Every week there seems to be a new story about a company cutting staff and pointing at artificial intelligence as the reason. It is unsettling, especially if you are job hunting or worried about your own role. So what does the actual data say, not the headlines, the data?
Every month, the outplacement firm Challenger, Gray and Christmas publishes one of the most closely watched job cuts reports in the United States. Their June 2026 numbers are out, and they tell a more complicated story than the scary headlines suggest. Here is what is actually happening, and what it means for your career.
What the newest jobs report actually shows
In June 2026, U.S. employers announced 45,849 job cuts, according to Challenger, Gray and Christmas. Of those, 14,029, or 31 percent, cited artificial intelligence as a reason. That made AI the single leading cause of layoffs in June, and it has now held that top spot for four months in a row. So far in 2026, AI has been cited in 101,743 job cut announcements, about 23 percent of all cuts this year.
That is a real trend, and it is worth taking seriously. But it is only half the picture.
AI’s share is rising, but total job cuts are actually falling
Here is the part that rarely makes the headline: total job cuts in the first half of 2026 are down 40 percent compared to the same period last year, 443,604 versus 744,308. June’s total was also down 53 percent from May and slightly lower than June 2025. AI is becoming a bigger slice of a smaller pie. Companies are cutting fewer jobs overall, but when they do cut, they are naming AI as the reason more often than before.
That distinction matters. It is not that AI is causing a flood of new layoffs on top of everything else. It is that AI has become the explanation companies reach for as they restructure, whether or not it is the whole story.
Which industries are actually affected
The cuts are not spread evenly. Technology led every sector in June with 15,503 job cuts, bringing its 2026 total to 139,156, an 83 percent jump from the same point last year. Tech now accounts for close to a third of all job cuts announced this year. Transportation has also seen a sharp rise, up 387 percent year over year, though that appears tied more to costs and trade conditions than AI specifically. Sectors like food production and health care products saw far smaller increases.
If you work outside tech, especially in transportation, services, or manufacturing, the picture looks quite different from what the AI headlines suggest.
Hiring is actually up this year
This is the detail that gets buried most often. Employers have announced plans to hire 91,405 workers so far in 2026, up 10 percent from the same period in 2025. Challenger’s own analysts called this a break from the pattern seen since 2020. Companies are not just cutting, plenty are also hiring, even in the same stretch where AI is the top-cited reason for layoffs.
Tip: when you read an AI-layoffs headline, check whether it mentions the hiring side too. A report that only covers cuts is telling you half the story.
What this means for you
From my own experience working across websites, online tools, and digital projects, the roles that feel safest right now are the ones where AI is a tool you use, not a replacement for the whole job. Companies are not eliminating judgment, client relationships, or hands-on skilled work. They are automating the repetitive middle of a process and asking fewer people to run the tool that does it.
If your role is concentrated in tech, especially in repetitive or process-heavy tasks, it is worth taking the AI trend seriously and building AI fluency now rather than later. If you are outside tech, the data suggests the AI-layoffs wave has not hit your sector nearly as hard, even if the headlines make it feel universal.
How to protect yourself either way
- Learn to use AI tools in your actual job, not just casually. Comfort with AI is increasingly part of the job itself, not a bonus skill.
- Keep your job search materials current even when you are not looking. Our guide on how to use AI in your job search covers a practical starting workflow.
- Track how interviews are changing too. Many employers now use AI in the hiring process itself, covered in our guide to AI job interviews and how to prepare.
- Understand the wage side of this shift, not just the risk side. We covered that in why AI skills now pay more.
For a deeper look at which specific roles are growing and shrinking by 2030, our earlier piece on whether AI will take your job breaks down the longer-term projections from the World Economic Forum. This month’s Challenger data is the near-term temperature check, and right now it reads as real but uneven, not the sweeping collapse the headlines imply.
Common Questions
Is AI really the number one cause of layoffs in 2026?
Among the reasons companies report to Challenger, Gray and Christmas, yes, AI led in June 2026 for the fourth month running, cited in 31 percent of that month’s cuts. It is the leading reported reason, not necessarily the only cause behind each individual decision.
Are total layoffs going up or down in 2026?
Down. Total job cuts through the first half of 2026 are 40 percent lower than the same period in 2025, even though AI’s share of the reasons given has grown.
Which industries should be most concerned about AI-related job cuts?
Technology has been hit hardest, accounting for close to a third of all 2026 job cuts and an 83 percent increase from last year. Other sectors have seen far smaller AI-related impact so far.
Final takeaway
AI is genuinely reshaping how companies think about headcount, and that is worth paying attention to, especially if you work in tech. But the full data also shows fewer total layoffs than last year and more hiring than in 2025. The honest takeaway is not panic, it is preparation. Learn to work with AI tools in your field, keep your skills current, and check the actual numbers before you let a headline set your mood for the week.
by admin | Jul 14, 2026 | AI Guides
Ever asked ChatGPT a question and had it casually mention something you told it two weeks ago? That’s not a coincidence, and it isn’t the AI “learning” the way a person does. It’s a specific feature called memory, and by mid-2026 all three major AI chatbots, ChatGPT, Gemini, and Claude, have some version of it switched on by default for most users.
If you’ve never actually checked what these tools remember about you, it’s worth five minutes. This guide walks through how AI memory works, what each chatbot stores, and how to see (and delete) what it knows. If you’re still getting comfortable with the basics first, our simple explanation of what AI is is a good place to start.
How does AI memory actually work?
AI memory isn’t the model “learning” facts about you the way training data works. It’s closer to a running notes file. As you chat, the system behind the large language model picks out details worth keeping, your job, your ongoing projects, your preferences, or things you’ve explicitly asked it to remember. That summary gets pulled into future conversations so you don’t have to repeat yourself every time.
The important distinction: memory is not the same as the model being retrained on your chats. Memory is a stored, editable summary tied to your account. Whether your conversations are also used to improve the underlying model is usually a separate setting, and it’s worth checking each tool’s data controls if you’re curious.
How ChatGPT’s memory works
OpenAI runs two connected systems: saved memories (specific facts you or ChatGPT flagged, like “I’m vegetarian”) and reference chat history (a broader synthesis of past conversations). Both live under Settings, Personalization, Memory, where you can see, edit, or delete anything ChatGPT has stored. Turning off “reference saved memories” also turns off chat history reference. If you want a conversation that leaves no trace at all, Temporary Chat skips memory entirely, according to OpenAI’s own Memory FAQ.
How Gemini’s memory works
Google’s Gemini builds personalization from your past Gemini chats, plus, if you choose to connect them, activity in certain Google apps. You can review and manage everything it has stored from the personalization settings inside Gemini Apps, and Google states it will not use these memories to train its models. One catch worth knowing: these personalization features aren’t available on work, school, or supervised accounts, only personal Google Accounts, per Google’s Gemini Apps Help Center.
How Claude’s memory works
Anthropic’s Claude builds a memory summary from your chat history that updates roughly every 24 hours, plus a separate, isolated memory space for each project you create. You can view and edit everything under Settings, Capabilities, and you get two off switches: pause memory (stops new memories without deleting old ones) or reset memory (deletes everything, permanently, with no undo). Claude also has an incognito chat mode for one-off conversations it won’t remember at all, according to the Claude Help Center. If you’re weighing which of these three tools fits you best overall, our ChatGPT vs Gemini vs Claude comparison covers more than just memory.
Why this matters for your privacy
Here’s the part worth pausing on: memory only works because the AI is storing what you tell it, sometimes including things you didn’t mean to have remembered long-term. Mention a medical detail, a work conflict, or a financial number in passing, and it can end up summarized and resurfaced later, or quietly shaping how future answers are personalized for you.
Tip: before typing anything sensitive into an AI chat, ask yourself whether you’d be comfortable seeing it referenced back to you next week. If not, use a temporary or incognito chat instead.
From my own experience working with websites, online tools, and cybersecurity, the easiest habit is checking memory settings once a month, the same way you’d check app permissions on your phone. It takes two minutes and it’s the only real way to know what’s actually being stored about you.
How to check and control what AI remembers
- ChatGPT: Settings > Personalization > Memory > Manage
- Gemini: gemini.google.com > Settings > Saved info / personalization
- Claude: Settings > Capabilities > View and edit memory
All three let you delete individual memories, wipe everything, or turn the feature off completely. None of this deletes your actual chat history unless you delete those conversations separately, memory and chat history are stored and controlled independently. For a broader look at staying safe while using these tools day to day, see our guide on how to use AI safely.
Common Questions
Does turning off memory delete my past conversations?
No. Turning off memory stops new memories from being created, and in some cases deletes what was already summarized, but your actual chat history is a separate setting you manage on its own.
Is AI memory the same as the model training on my data?
Not automatically. Memory is a personal, editable summary tied to your account. Whether your chats are also used to improve the underlying model is usually a separate toggle, worth checking in each tool’s own data controls.
Can I use ChatGPT, Gemini, or Claude without memory at all?
Yes. All three let you turn memory off completely, and each has a no-memory mode for individual chats, Temporary Chat in ChatGPT, incognito chats in Claude, and Gemini’s personalization simply won’t apply if you never connect it.
Final takeaway
AI memory is genuinely useful, it’s why these tools feel less repetitive the more you use them, but it only works because it’s quietly storing details about you. You don’t need to be paranoid about it. Just know it’s there, check what’s saved every so often, and reach for a temporary or incognito chat when you’d rather something wasn’t remembered. That’s really the whole trick to using it well.
by admin | Jul 13, 2026 | AI Tools
You just left a long online meeting, and now you are staring at a few messy lines you typed while half-listening. Who agreed to do what? What was that deadline? If you have ever tried to write notes and follow the conversation at the same time, you know it rarely works well.
This is where AI meeting assistants come in. These tools can join your call, write down every word, and hand you a clean summary with the action items already pulled out. In this guide I will explain what they are, which ones you may already have, how to use them, and the privacy side that most people forget to check.
What is an AI meeting assistant?
An AI meeting assistant is a tool that listens to your meeting, turns the speech into text, and then writes a short summary for you. Most of them give you three things: a full transcript of what was said, a summary of the main points, and a list of action items or next steps.
There are two main types. Some are built right into the meeting apps you already use, like Google Meet, Microsoft Teams, and Zoom. Others are separate tools that send a small bot into your call to take notes. Both do a similar job, so the right choice usually depends on which apps your team already lives in.
The AI note-takers you may already have
Before you sign up for anything new, check the apps you use every week. The big three all have their own note-taker built in.
- Google Meet has a feature called Take notes for me. Powered by Gemini, it captures the meeting in a Google Doc and adds a summary and action items. It is available on Google AI Pro and Ultra plans and eligible Workspace accounts.
- Microsoft Teams uses Copilot and its intelligent recap to summarize who said what and suggest action items. You need live transcription turned on, plus a Teams Premium or Microsoft 365 Copilot license.
- Zoom has AI Companion, which creates a meeting summary with key points, decisions, and next steps a few minutes after the call ends. An account admin needs to switch it on first.
Standalone tools like Otter
If your team jumps between different meeting apps, a standalone assistant can be easier. Otter is one of the best known. You connect your calendar, and its bot joins your Zoom, Google Meet, or Teams calls automatically. It writes a live transcript, builds a summary, and even lets you ask questions like “what were my action items?” after the call.
Otter is not the only one. Tools like Fireflies and Fathom do similar work, and several offer a free tier for light use. Free limits change often, so check the current plan on the tool’s own site before you rely on it. For a wider look at everyday AI tools, see our guide to useful AI tools for daily work and study.
How to use an AI meeting assistant
The setup is usually simple. Here is the basic flow that works for almost any tool.
- Turn on the note-taker before the meeting, or connect your calendar so it joins on its own.
- Tell everyone on the call that it is being recorded and transcribed.
- Run the meeting as normal and let the tool listen in the background.
- After the call, open the summary, read it, and fix anything the AI got wrong.
- Share the clean notes and assign the action items.
Where these tools really help
From my own experience running websites and online projects, the transcript is nice, but the real time saver is the action-item list. Instead of rewatching a call to find one decision, I get a short list I can drop straight into my task app. If you want to build on that, our guide on using AI for time management shows how to turn those items into a real plan.
Students get a lot out of these tools too. You can record a lecture (with permission), get a full transcript, then drop it into a tool like NotebookLM to turn it into a study guide or a quick quiz.
The privacy part people skip
Here is the part I always slow down on, because it touches privacy and security. An AI meeting assistant records and stores everything that is said, and sometimes that includes sensitive information. A few simple habits keep you safe.
First, always tell people they are being recorded. In many places you are legally required to get consent before recording a conversation, so do not treat it as optional. Second, avoid recording calls where people share private or confidential details unless everyone agrees. Third, check what the tool does with your data. Zoom, for example, says it does not use your meeting content to train its AI models, while Microsoft says Teams recap data is stored based on your organization’s own admin policy.
Quick tip: Treat every AI meeting summary as a first draft, not the final record. The AI can mishear names, numbers, and decisions, so read it once and correct it before you send it to anyone.
If you want a fuller checklist, our guide on how to use AI safely and protect your privacy covers what to share and what to keep out of any AI tool.
Common questions about AI meeting assistants
Are AI meeting assistants free?
Some standalone tools offer a free tier for a small number of meetings, while the built-in features in Google Meet, Teams, and Zoom usually need a paid plan. Because free limits and prices change often, check the current plan on each tool’s official site.
Do AI meeting notes make mistakes?
Yes. AI transcription is good but not perfect. It can get names, numbers, and technical words wrong, and it can misread who said what. Always review the summary before you treat it as an official record.
Is it legal to record a meeting with an AI note-taker?
It depends on where you and the other people are. Many regions require you to tell participants and get their consent before recording. The safe habit is to always announce that the meeting is being recorded and let people opt out. This is general information, not legal advice, so check your local rules for important calls.
Final takeaway
AI meeting assistants can save you real time by handling the boring part of meetings, so you can actually pay attention. Start with whatever is already built into Google Meet, Teams, or Zoom, or try a free standalone tool like Otter. Just remember the two rules that matter most: tell people they are being recorded, and always check the summary before you trust it. Do that, and you get the time back without the headaches.
