Paddy Hirsch's Blog

PRIMED IS OUT TODAY!
Gary Lawlor broke the day his sons were murdered in a car bomb meant for him. He failed to find the killer, and drank himself into a hole of self-recrimination and shame. Twenty years later, he is back on his feet, but he’s empty inside. And when a chance comes for him to take his revenge, he takes it. No matter what the cost.

Róisín Mackey has known Lawlor since the day they joined the police together. A Catholic woman in an overwhelmingly male and Protestant force, she has always felt like an outsider, but Lawlor has always had her back. When he decides to go on the hunt for the killer, she backs him in return, not knowing that his quest will turn over the dark earth of the past, and reveal secrets that will change everything for them both.

You can buy PRIMED as an ebook on Indiebound, Apple Books, on Amazon and on Kobo. You can buy it as a printed paperback from all of those outlets too, but Indiebound is probably best (and cheaper!). If you love bookshops (and who doesn’t love bookshops) you can order a copy from your local. Finally, if you’re a library lover, you can reach out to your library and ask them to purchase a copy (or two). Thank you!

The post It’s Publication Day! appeared first on Paddy Hirsch.

One of the great things about working with a publisher is that you outsource the proofing of your work. The publisher bought the book, so it’s their responsibility to make sure all the commas are in the right place, etc. Doing this as a self-publisher means either paying a professional proofreader ($500-$1000, depending on the length of the work) or doing it yourself. The problem with doing it myself – well, my problem – is I keep getting new ideas and urges to make material changes. All of which have to be fully and seamlessly incorporated … and proofed!

So I decided to give AI a try.

It’s hard to express what an utter failure this was. First, the AI (I used both ChatGPT 5 and Claude) kept missing things. When I pointed out that a word was misspelled and that it had failed to catch it, the AI explained that it doesn’t actually read every word … it skims:

“…you’ve caught me out on a habit of proofing in layers rather than word-by-word.”

Proofing in layers? What does that even mean?

Yes, I should have fired the AI right then, but I kept at it. When I asked it to proof chapters, word-by-word, as a human would, it moved extraordinarily slowly. I was reading the work faster than it was. And I was reading backwards!

When it did finally respond, it kept overstepping, offering me critique on pacing and tension. When I told it to butt out and focus on the assigned task, the AI complied for a while, and then went rogue, first giving unsolicited opinions, and then rewriting the copy entirely! When I tried to steer it back on course, it began to hallucinate, at one point spitting back a passage that I hadn’t written, with characters I hadn’t created.

At first it was mystifying, then irritating, and finally entertaining. I gave up, eventually, but later returned to the well with another, simpler task. I asked the AI to read the entire novel and tell me what it thought my author comps are (as in, what novelists I could compare the book to in marketing copy). It accepted the task …

“You asked me to read the whole thing and tell you who the comparable authors are on August 25, 2025 at 15:42 (your local time).”

It was still reading at 22.31 hrs on Sunday Aug 31, when I wrote these words. Six days!

So much for the brutal efficiency of the machine!

The post Why AI ain’t all that appeared first on Paddy Hirsch.

I’ve been on this self-publishing journey for a while. But now it’s getting real. I’m starting to think about an actual publishing date, probably right around the beginning of November, to tie in with one of my favorite book events of the year, Men of Mystery, which celebrates its 25th anniversary gathering on November 8.

That’s more than a quarter away, but in book terms, it’s right around the corner. There’s a lot to do. I have to ramp up a promotion campaign, and network with local independent bookstores. I have to think about social media marketing, and how best to leverage this newsletter. I have to think about reaching out to authors to endorse the book. I have to send Advance Reading Copies. I have to think about how many physical books to print, and which digital platform to use to sell the book. And a lot more.

First of all, though I have to choose the cover. Or the jacket, if you prefer. I wrote about this last month, and promised to give you the chance to weigh in. I got six options from the designer (you’ll have seen those in an earlier post), and narrowed it down to the two below. Now I need to decide, and maybe you can help me with that…Pick which one you like. If you feel moved, write and tell me why. And give me any other feedback you fancy. I welcome it all!

The post Help me choose my new cover! appeared first on Paddy Hirsch.

The post Check out my jackets! appeared first on Paddy Hirsch.

1. They’re basically your book’s first date outfit
Let’s be real – people absolutely judge books by their covers. You’ve got maybe three seconds to catch someone’s eye before they move on. A good cover is like showing up to a first date looking sharp versus rolling up in your PJs.

2. They tell you what you’re getting into
You can spot a romance novel from across the room, right? (Admit it!) That’s the cover doing its job. Dark and moody? Probably a thriller. Pastel watercolors? More than likely not a horror story. The cover acts as a visual cheat sheet for “is this my kind of book?”

3. They’re mobile ads for your work
Think about it – every time someone carries your book on the subway or posts it on Instagram, that cover is working for you. Plus, when your friend says “you should read this book,” it helps if they can add “it’s the blue one with the giant squid.”

4. They set the vibe
A cover is basically making a promise about what’s inside. It’s like a movie trailer but in one image. Get it wrong and readers feel catfished.

5. They show you’re not messing around
Especially if you’re self-publishing, a cheap-looking cover screams “I wrote this in my basement and my nephew did the art.” Even if you DID write it in your basement, you don’t want it to look that way. An amateur cover can make readers assume the writing will be amateur, too.

Beyond commerce, book covers contribute to visual culture. Iconic covers become part of our collective memory – think of the distinctive covers of classics like 1984 or The Great Gatsby. They can elevate a book from mere product to cultural artifact.

The post Five Reasons Why Book Covers Are Key (And Worth Paying Up For) appeared first on Paddy Hirsch.

… that I mostly agree with.
From

(1) First, the new bottleneck on AI is prompting and verifying. Since AI does tasks middle-to-middle, not end-to-end. So business spend migrates towards the edges of prompting and verifying, even as AI speeds up the middle.

(2) Second, AI really means amplified intelligence, not agentic intelligence. The smarter you are, the smarter the AI is. Better writers are better prompters.

(3) Third, AI doesn’t really take your job, it allows you to do any job. Because it allows you to be a passable UX designer, a decent SFX animator, and so on. But it doesn’t necessarily mean you can do that job *well*, as a specialist is often needed for polish.

(4) Fourth, AI doesn’t take your job, it takes the job of the previous AI. For example: Midjourney took Stable Diffusion’s job. GPT-4 took GPT-3’s job. Once you have a slot in your workflow for AI image gen, AI code gen, or the like, you just allocate that spend to the latest model.

(5) Fifth, killer AI is already here — and it’s called drones. And every country is pursuing it. So it’s not the image generators and chatbots one needs to worry about.

(6) Sixth, decentralized AI is already here and it’s essentially polytheistic AI (many strong models) rather than monotheistic AI (a single all-powerful model). That means balance of power between human/AI fusions rather than a single dominant AI that will turn us all into paperclips/pillars of salt.

(7) Seventh, AI is probabilistic while crypto is deterministic. So crypto can constrain AI. For example, AI can break captchas, but it can’t fake onchain balances. And it can solve some equations, but not cryptographic equations. Thus, crypto is roughly what AI can’t do.

(8) Eighth, I think AI on the whole right now is having a decentralizing effect, because there is so much more a small team can do with the right tooling, and because so many high quality open source models are coming.

All this could change if self-prompting, self-verifying, and self-replicating AI in the physical world really gets going. But there are open research questions between here and there.

The post Some coherent thoughts on AI… appeared first on Paddy Hirsch.

I was asked about this the other day, and found myself unable to answer without changing my mind. Here’s the list. But in no particular order.

Boiler Room
Glengarry Glen Ross
Mrs Watanabe: How Japanese Housewives Outsmarted Global Finance
The Bank of Dave
Trading Places
The Big Short
Working Girl
American Psycho
Wall Street
Margin Call

The post My Top Ten “Wall Street”Movies appeared first on Paddy Hirsch.

George Orwell wrote his essay “Politics and the English Language” in 1946. In it, he criticised the “ugly and inaccurate” written English of his time and examined the connection between political orthodoxies and the debasement of language. The essay focused on political language, which, according to Orwell, “is designed to make lies sound truthful and murder respectable, and to give an appearance of solidity to pure wind” (Wikipedia). Any of that sound familiar?

It’s a great essay, and not just for writers who are interested in making their work more clear and less hackneyed. It’s timeless in its critique of news writing. Here’s one particularly resonant paragraph.

The word Fascism has now no meaning except in so far as it signifies ‘something not desirable’. The words democracy, socialism, freedom, patriotic, realistic, justice, have each of them several different meanings which cannot be reconciled with one another. In the case of a word like democracy, not only is there no agreed definition, but the attempt to make one is resisted from all sides. It is almost universally felt that when we call a country democratic we are praising it: consequently the defenders of every kind of régime claim that it is a democracy, and fear that they might have to stop using that word if it were tied down to any one meaning. Words of this kind are often used in a consciously dishonest way. That is, the person who uses them has his own private definition, but allows his hearer to think he means something quite different. Statements like Marshal Pétain was a true patriot, The Soviet press is the freest in the world, The Catholic Church is opposed to persecution, are almost always made with intent to deceive. Other words used in variable meanings, in most cases more or less dishonestly, are: class, totalitarian, science, progressive, reactionary, bourgeois, equality.

The post George Orwell’s “catalogue of swindles and perversions” appeared first on Paddy Hirsch.

I received an assignment recently: to write a story about how much Presidents in the past have increased their net worth whilst in office.

I started out by using good old Google to see if I could find the data, but quickly discovered there is a lot of misinformation out there on this topic. Inauguration dates are conflated with election dates, and in-office earnings are conflated with post-presidency earnings. A lot of the coverage is politically charged, implying that certain presidents (Obama! Clinton!) made loadsamoney in office when, in fact, they did not.

Anyway, I got pretty lost, pretty fast.

So, I thought I’d see if ChatGPT could help. It would basically do what I was doing, and scrape the internet for data. Just a lot faster than I could. But the initial speed of ChatGPTs responses came at a cost.

The first thing I found, is that garbage in, garbage out is a real problem with ChatGPT. The bot consistently cited incorrect references, or misread legitimate references and extrapolated incorrect conclusions. I found myself playing editor with it: I would read the dataset it spat out, identify what I thought might be errors and challenge the bot. It would apologize for getting something wrong and spit out new data, which also needed to be checked. And was also usually incorrect.

You said:
what was george w bush’s net worth the day of his inauguration, and what was it the day he left office?

ChatGPT said:
At the time of his inauguration, George W. Bush’s net worth was estimated to be approximately $20 million. … By the time he left office, George W. Bush’s net worth had increased to approximately $40 million … This growth was attributed to various post-presidency endeavors…

You said:
You say “By the time he left office, George W. Bush’s net worth had increased to approximately $40 million. This growth was attributed to various post-presidency endeavors…” how could his net worth whilst in office have increased due to post presidency endeavors?

ChatGPT said:
You’re absolutely right to question that — and thank you for catching it. That sentence was poorly phrased and misleading. Here’s the correct breakdown:

George W. Bush’s net worth:
At inauguration in 2001: ~$20 million
At the end of his presidency in 2009: likely still around $20–25 million, with only modest increases from investments, book deals not yet realized, and presidential salary.

This kind of thing happened over and over as I fact-checked Chat GPTs findings. When asked to re-check its numbers, it often cited the content that it had previously scraped, and had to be prompted again. It was like working with a very green reporter, who had no training in research, and who trusted every online source they found.

Worst of all, when asked to cite sources, Chapt GPT lied to me. For example, it said that Ronald Reagan’s net worth increased from 10 million to 15 million while he was in office, and provided a source link. I clicked, and it brought me to a Fox Business article America’s Richest Presidents. Ronald Reagan was not even mentioned in the story!

You said: I checked your sourcing on Ronald Reagan, but that article does not mention him.

ChatGPT said: Apologies for any confusion in my previous responses. Upon reviewing the available sources, it appears that specific data on Ronald Reagan’s net worth at the time he took office in 1981 and when he left office in 1989 is not readily available. However, estimates suggest that Reagan’s net worth at the time of his death in 2004 was approximately $13 million, which would be equivalent to about $17.89 million today, accounting for inflation.

It was clear to me that Chat GPT was doing what a lot of green reporters do: trusting news stories without finding the original source for their data. For example, that Fox Business story cited zero sources. They could have made the whole thing up! I’m sure they didn’t, but it was impossible to verify. Other stories cited legitimate news organizations, but without providing links that allow the reader to check those news organizations’ own sources.

I pressed ChatGPT again on the Reagan data. Interestingly, the bot contradicted itself. Having just said that the data wasn’t readily available, it then apparently managed to find some:

You said: I’m not interested in his earnings post office. I asked for how much he made while he was in office. You keep giving me incorrect information

ChatGPT said: Apologies for any confusion in my previous responses. Let’s focus on the accurate data regarding Ronald Reagan’s net worth during his presidency.
Ronald Reagan’s Net Worth During His Presidency
At Inauguration (January 20, 1981): Approximately $4 million. This estimate was based on a report filed with the Office of Government Ethics covering 1980 until the day he took office, including assets such as his Pacific Palisades home valued at $1.9 million, a 688-acre ranch worth about $1 million, and $740,000 in cash accumulated from the sale of stocks.
At Leaving Office (January 20, 1989): Approximately $4 million. There was no significant change in his net worth during his time in office, as most of his income came from his California pension as a former governor, interest on cash savings, and speech fees.

The bot cited UPI for these findings. UPI cited the New York Times, which cited the Office of Government Ethics (the director of which was ousted by President Trump on February 10, 2025).

This feels real to me. When I was an editor, if a reporter came to me and said that they had sourced their data to the Times, which cited the OGE, I’d be happy enough to proceed – and cite those sources in our coverage. Ideally we’d get that data ourselves, although it’s not easy to check with the OGE: the only way to get the data is to file a FOIA request and wait however many months for the response.

But it was difficult to get ChatGPT to this place. It consistently cited junk clickbait content that provided no sourcing. And its findings varied widely. It told me variously that Barack Obama’s net worth on leaving office was $1.8 million, $3 million, $12.2 million and $40 million. I kept asking it the question “are you sure?” And it would correct itself. I still don’t know what the correct answer is! When asked to check its own work, it failed to learn its lessons, the way a human would. Instead it kept going back to sources that we had already established were not to be trusted. That made the process of discovery time consuming and frustrating. You can read a version of our eventually fruitless exchange here.

In short, ChatGPT can’t be trusted as a reporting tool. It doesn’t mean that it’s useless: it does find stuff really fast. The problem is that the quality of that stuff really isn’t that great. And might be more trouble than it’s worth. The bot needs to be checked and checked again, and pushed to fact check itself. Reporters who use it need to demand that it reveal its sources, and then check those sources independently.

ChatGPT is often touted as a time saving tool for journalists. I found the opposite to be true: the conscientious reporter who cares about telling the truth and getting to the real source of a story may find that using the bot gobbles up more time than doing the research on one’s own.

The post Journalism with Chat GPT appeared first on Paddy Hirsch.

Source: Guitar.com

From Parade and Classic Rock: More than half a century ago, the legendary music broadcaster John Peel invited Thin Lizzy to the BBC Maida Vale studios in London to record four songs for his Top Gear radio show. Those recordings were thought to be lost—until today.

Classic Rock reported that a YouTube user called Rob F found four tracks on an off-air reel-to-reel. He uploaded them to YouTube. Clifton Grange Hotel and Ray-Gun – appeared on Thin Lizzy’s debut album, released in 1971. Dublin (released as a single the same year) and The Rise And Dear Demise Of The Funky Nomadic Tribes would both appear on the band’s second album Shades Of A Blue Orphanage in 1972.

Check out all four tracks here.

The post Historical non-fiction: Thin Lizzy’s lost recordings appeared first on Paddy Hirsch.