I think Medium has one of the best writing experiences on the internet. It's one of the main reasons I have been using the platform for so long. They have designed it in such a way that you can focus solely on your writing.

However, there is more to writing that just writing the finished article. A writer doesn't just sit down, bash out an article and press publish. If only it were so easy... 

There are different phases to producing a finished article. The idea phase, the research phase,  the "choosing a catchy title" phase (much more important than I initially realised) and many other elements that go into producing a well rounded article worth the readers' attention.

I used to have a convoluted process that involved different Notion templates, generative AI for the titles and 

 for choosing the images. I then had the added overhead of putting my articles on different sites. My 

 (I still can't work out if this is worth it).

The process worked but it was cumbersome. 

I wanted a tool that would allow me to do all of this from one place. We live in the world of AI now. I'm a software developer. Why not build what I wanted myself?

It's exactly what it says it is at the top of the homepage: "

Medriter is a local-first desktop app for writing articles and publishing them to Medium and your own blog — in one click.

For me the writing experience is so important. I have spent many hours over the past years working to improve my writing. There is something deeply therapeutic about writing and I wanted to keep the essence of that in the experience of this app.

One of the main features is the 'Focus Mode'. This enables the user, with a click of a button (or keyboard shortcut), to remove everything else from the UI.

I have split the writing flow into four parts.

This was the natural flow I had grown into over years of writing articles. I always have ideas for articles so it was imperative to have a place where all of these could be captured. 

The ideas section lets you capture all the things that come to mind in one place. I use it to begin arranging the structure of the piece, collect relevant links and start developing and flushing out my ideas.

Next up comes the "Write" part. This UI and UX is inspired by Medium's writing experience but with added features. 

Version history (so you can go back to parts you may have removed and they are not lost forever)

Keyboard shortcuts to bring up the main editor elements like headings, divider, lists etc.

"Grammarly" type tool for tightening, fixing grammar or rephrasing parts of the text - cmd + shift + a

Then comes the "Review" section. This is where AI enters the picture. 

I have thought long and hard about this. I came to the decision that it is acceptable and beneficial for AI to review my articles and provide feedback.

My ultimate goal as a writer is to become as good a writer as I can.

 We have a tool at our disposal that can provide clear feedback on ways to improve at this craft. I think it would be naive to ignore this tool altogether. 

However, it is one thing to have AI provide feedback but quite another for it to write the articles themselves. 

That is why the "Review" section is a separate tab in the UI.

 It is there to provide feedback but the UX should lead the user to write the article themselves.

Last but not least is the "Publish" tab. This is where you can push your articles to Medium and your own blog with one click. At the moment only 

 is supported for the blog format but other blogging platforms can be added depending on future demand. (Write me if you want a specific blog platform added!)

Another important part of this app is you own your data. This is a local app running on your machine. All the data is on your machine and backed-up there too. There are no sneaky cookies, no ads, no passing of your data around to other companies for profit. 

It's just your writing, saved to your machine and you are free to do what you want with it.

Copy Article Button - This allows you to copy the whole article (images included) with a click of a button and paste where ever. I use this for Substack.

AI suggestions for Titles and Subtitles - I always find this part of producing articles difficult so it's good to have a helping hand in this area.

Backups - All your content is backed up locally to a folder of your choice. Therefore, your writing content will always be safe. Tip: backup to a cloud provided service like Google drive.

Search popup - Allows you to jump to any article or idea by just pressing cmd + p

 It currently only runs on MacOS. There is a 7 day trial period and then if you want to continue using the app it's a one time fee of $29. 

Most apps these days are subscription based but I really wanted to avoid that as I know these subscriptions add up. With the one time fee it allows you to get all the small improvements and fixes that are in the version you buy. Current version is v1.

First and foremost I am very happy with the result of Medriter. This isn't some weekend vibe-coded app patched together by bad code and hope. 

 The first few years the idea was brewing away in my head. Then in the last 6 months it became an actual reality.

I am using it everyday to write and it's enabling me to focus solely on the my writing.

It's now time to release it to the wild. I was a little hesitant to do this because I am sure it won't be to some people's taste and there may be some negative feedback. However, I am hoping it will be able to help some writers along their journey and provide a better writing experience for them.

Please let me know if you use the app and if it provides a good writing experience for you. If you think of ideas or improvements please let me know. Happy writing!

I Spent 6 Months Building the Writing App I Always Wanted (One Click Publish to Medium and My Blog)

I have had a constant love-hate relationship with X since its early inception. I've gone through periods of using it extensively and then other periods where I wouldn't touch it for years.

Ultimately I want to know if I should be using X as a Software Developer with "Should" being at the crux of this inquiry. Will it make a significant enough impact on my career which would deem it worthy of the non-significant time investment? In this article I want to face this crucial question head on. 

There are obvious benefits to using twitter - Learning about new tech, finding out about upcoming events or getting great tips about the latest hyped terminal setup (

I've discovered many non-trivial things from scrolling around on X - I first learnt about 

 for example - which have definitely had an impact on my development career.

It makes you feel connected to a community. Being a developer means spending many hours by yourself so it's easy to become a little isolated. X makes it easy to find like minded individuals and feel a certain connection even if it is only a digital one.

However, it's not all sunshine and butter biscuits. 

Like any technology, X certainly has a dark side. In X's case it is a rather sinister and brutal dark side. 

Steering away swiftly from the obvious political rabbit-hole I could go down, I want to focus solely on the down sides which I personally experience. 

First up are the posts that are perversely designed to rile you up the wrong way. To cause a gut reaction. To get your ever rising blood pressure to shoot up a few more notches. 

X deliberately shows you these posts to generate engagement and help that dollar counter tick over. However, the negative mood created can linger for a long time afterwards. This can have a nasty knock-on effect in my real life as I mull over the post in my mind.

 about creating an alias 'please' instead of using sudo as sudo is passive aggressive. I got riled up almost instantly with a gut reaction and responded. Almost always I regret responding in this manner later on. However, sometimes my emotions get the better of me.

I often find myself unconsciously opening a new tab and typing in "x.com". It's a cognitive comfort blanket. A quick escape to distract myself from whatever uncomfortable task I faced me. 

Then 15 minutes later you realise you've wasted a bunch of time and haven't got any work done and likely in a worse mood than when you started.

I think there is a scientific proportional relationship for this - 

the longer you spend on X the higher your FOMO

. It's probably not an exact correlation but in my case it leaves me feeling like a dinosaur who is living in the dark ages compared to all the cool kids working with all their modern jazzy new tools.

Do the benefits outweigh the disadvantages? Honestly it's hard to say but the older I get the more I cherish a healthy headspace. This gives the disadvantages more weight in this comparison.

But it also does depends on how you use X. Doom scrolling vs having a clear plan of attack makes a huge difference. What is a good strategy on X though?

This is something I have struggled with since day 1 and the conclusion I have come to (which isn't very helpful) is "it depends".

X is a very different experience if you are a well known developer versus being a relative unknown. For the likes of 

, they can ask a question into the X ether and they will receive hundreds of responses. If I were to ask the same question then 

which is interesting in itself because this whole strategy piece has the underlying philosophy that there is a goal in X and that goal is to acquire as much attention as possible

), I usually find myself answering the questions these "big fish" ask. This has been the most successful approach if I want to get any kind of reaction or attention.

But is this the optimal way to use X? I think there is no right answer to this as it all depends on why you're there. 

For me, when I tweet into the ether and get zero interactions it just all seems a bit pointless. It feels like sitting in a cafe surrounded by people and just talking to myself. 

There are many people all over X promising a "guaranteed strategy" to grow your X followers and maybe some of them work. But I believe that ultimately you have to have an overall goal. Like selling a course or promoting a product. Then it makes more sense and you can use X as one more marketing channel.

After much consideration I have decided to ultimately stop using X. My clear headspace is too important to me these days. Since starting to use X regularly again, more of my time away from the computer is spent imagining replies or writing posts. I have found I too easily get involved in reactionary posts. I more often than not react negatively to someone else's opinion and this is clearly impacting my overall mental wellbeing.

I have a clear objective in my life right now. 

Build quality software (with the help of AI) and solve real problems for real people which generates a second income stream.

Therefore I have realised I should be dedicating what time I have to this end. X does not help with this objective.

The hardest part of this will be not casually opening a tab and typing in "x.com". It's a comfort blanket for me so I will have to find an alternative to this that doesn't give me the negative headspace. 

Similarly, I stopped watching the news 5 years ago and it was one of the best decisions I have made. I think doing the same with X will also bring an overall benefit to my life. Maybe I will miss out on some cool news and trends but ultimately it is just unneeded noise.What's your opinion on this? Do you use X regularly? Do you think it's an overall net positive for you? If not, then how do you regulate the negativity?

Why I Quit X as a Software Developer (After 10+ Years of Love-Hate)

I’m writing to you from the future. The year is 2037 and the internet is dead. It’s all but gone. How we got here is both remarkable yet totally obvious. It was even predicted in the “Dead Internet Theory” yet nothing was done about it. AI did this, that much is certain. It thrived on all of human’s greatest weaknesses — greed, pride, sloth… and before we knew it, it was too late. 

Without the internet we have been thrown back into the dark ages. Millions of jobs were obliterated almost over night. Economies plummeted into the abyss. It didn’t take long for the food shortages to arrive and “The Great Hunger” to prevail amongst societies. Social unrest soon followed and now death is heavy in the air.

You must do something to prevent this happening. The future we are currently experiencing must be avoided at all costs. However, it is a tricky and deceptive road that lays ahead of you. This isn’t an “End Boss” type of situation. There is no mighty Thanus to slay and then we all live happily ever after. No, this is far more insidious. This is far more subtle and, dare I say… tedious. This is the poor unsuspecting frog, being slowly and horribly boiled to it’s untimely yet all too predictable death.

See, the internet didn’t just stop working one day. No, it was quite the opposite — it died piece by piece. The ebb of the AI slop lapping at the proverbial cliff edges slowly but surely eroding it away.

Software started deteriorating, both in terms of quality and effectiveness. Again, this can be traced back to the emergence of generative AI. It seemed like such a marvel during its inception, allowing developers to produce code at an astonishing rate. Reports around the world of 10 times productivity and in the hands of those who knew what they were doing it was incredibly powerful.

Problems did eventually start to appear though. Like in all such stories it happened when humans started cutting corners, being lazy and accepting whatever was produced by the AI, all in the pursuit of greedy corporate targets.

Software started becoming unreliable at a mass scale. Critical services — once the pinnacle of engineering expertise — started failing. At first for minutes but this soon raised to hours and then even days. Imagine for example when the Flight Management Systems started failing. Planes were literally falling out the sky. All planes had to be grounded for weeks halting all international travel. It was pure chaos and we know how humans react to chaos. 

And we had no real means to fix it. More and more experts were relying on generative AI to get them out of trouble and at a certain point it just wasn’t able to. 

It really turned nasty when the power stations started failing. Blackouts pervaded certain areas of the USA for days. I remember in 2033 when New York experienced a total blackout for 17 days in mid January. People were without heat or electricity in the coldest month of the year. It was devastating. The very old and very young huddled together for a shimmer of warmth were still succumbing to the inevitability of the bitter cold. 

Even then there was no turning back. Our dependence on AI and their swarm of busy little agents was far too high. Just when we thought we were back on track and the critical issue had been fixed, another one reared its ugly head. Engineers had become cumbersome and complacent — the ones that were left anyway — they were more coordinators than engineers. It had reached the point where even the most advanced engineers in the world struggled to understand what the AI had created in the code — if you could even call it code anymore.

You see they started creating their own coding language. It was a marvel when first introduced. “AGI!” was echoed around the globe. We really thought it had been achieved. We didn’t understand how it possibly could have done this but we also didn’t really care all that much. The fact it now appeared to be doing things with software we had only ever dreamt about was astonishing. We basked in our own glory. We confidently and naively assumed all software problems had been solved. We could now move on to bigger and better things like conquering the solar system and then the universe.

The folly of our age making these granduous assumptions. We are not moving onto anything, we are fighting for our survival. 

Please heed my advice. Don’t trust the LLMs. Don’t believe they are the answer. I know it’s probably too late even for you but you must try. 

The Dead Internet Theory Came True — Here's How It Happened

I did some research online and found the 

 from Aiper. It blew me away when I used it. It’s built with quality in mind and does a great job of cleaning the pool. It wasn’t cheap but it was very much worth it. When something works really well it’s just so satisfying.

I get the same feeling when I use Tanstack Query

. I have been using it for years now and it’s my go-to library for all things data fetching related. I recommend it to all developers who are getting into frontend, it’s such a better experience than trying to do the same thing without this library. Let’s dive into why it’s so good and why I recommend you try it out on your next project.

 is a library that helps you handle data fetching in your application. It comes with some very sensible defaults and has a bunch of useful functionality for you out of the box so you don’t have to worry about it.

We’re talking about things like cache, query keys to help with invalidating and refetching fresh data and a whole lot more.

I’ve been using Tanstack Query since the days it was called ‘React Query’ so it’s stayed with me through thick and thin. I trust it completely. 

A big reason for this is because of the man behind the whole Tanstack suite —

 — Whenever I hear him speak, his approach is always extremely sensible and well thought through. It’s obvious he thinks deeply about his work and he is the type of person who is able to clearly see the heart of the problem and go straight after it (a rare gift these days).

Let’s get into why you should use this library in your next project.

I’m going to focus on the useQuery hook. This is a hook which you can give any Promise based method (GET or POST) to fetch data from a server.

First lets look at an example in React of fetching a TODO from a server the traditional way:

With this approach you have to do a few things yourself:

Run everything through a useEffect so the data is fetched when the component loads

When using the useQuery hook the initial code is reduced and — in my opinion — is much more readable:

A queryKey is provided to the useQuery hook — we’ll get back to this as it’s very useful later on when we get to invalidating queries.

Loading and error state are handled by the useQuery hook so we don’t have to worry about managing it ourselves.

The useQuery hook is typed so we know exactly what to expect in each potential scenario.

We’re doing the same thing in about half as much code.

Tanstack chooses very sensible defaults out of the box and for many standard api requests it doesn’t require much tweaking. However, there are a bunch of knobs you can tweak and tune if you need to.

One great example is refetchOnWindowFocus — this option defaults to true but very often I don’t want this behaviour. I work on apps where the data doesn’t update too often and the user navigates around many different browser windows.

When the user returns back to the original app it was very annoying that the data was refetching every time.

With the tweak of this option I could turn it off and the data would only refetch after the stale time was reached.

It’s as easy as adding in fields to the object passed into the useQuery hook.

For the full set of options you can see the 

Tanstack query comes with default caching. It comes with a default gcTime (used to be cacheTime in v4) of 5 minutes and the default staleTime of 0. gcTime is the time in milliseconds that unused/inactive cache data remains in memory. staleTime is the time in milliseconds after data is considered stale.

For normal queries I don’t usually change these settings as they give you the functionality you need. But recently I’ve had use cases where I needed to use an api service to grab images that are generated on the fly. However, once the image is generated it doesn’t need to change. Therefore I set the gcTime and staleTime to Infinity so once the image is fetched the first time it never needs to be fetched again. 

The cache’s garbage collection is disabled and the data is never considered to be stale.

 The app can keep using the same image on the UI whenever it needs it.

This is quite a niche use case but the fact you can control how long the data in a query should be cached is very useful.

Invalidating queries becomes very useful as your app grows. Let’s say you have a page which uses the useQuery hook to fetch some data. That hook will have a key — something like [‘todos’] — this key acts as something that Tanstack Query can utilise when it needs to.

On another part of the UI you are updating some data and you want to make sure once the data is successfully updated the “todos” data is refetched. To do this you can invalidate this key “todos” so the query is then ‘stale’. If this current data is rendered on the UI it will trigger Tanstack to refetch the data. The code look something like this.

The power to be able to retrigger the fetching of specific data depending on different user interactions is very powerful, especially across larger dynamic applications and it’s something that I use often.

Choosing the right tool for the job is part of being good at your craft and it’s best learnt with experience. In software it’s no different except maybe the sheer range of tools to choose from.

Tanstack Query is one of those stand out tools that I think any developer working on the frontend should be aware of. It’s default functionality covers most standard use cases but it also comes packed with a load of customisable elements.

The creator — Tanner Linsley — has his head screwed on and speaks a great deal of sense, which is sometimes lacking in this crazy fast paced world we have created. When you find people like this in your industry, I advise you to keep a close eye on what they’re working on and always try out their creations.

I’ve Used TanStack Query for 5+ Years — Here’s Why I Still Recommend It to Every Frontend Dev

It amazes me how so many smart people can be so wrong. For the past 3 years many industry leaders — Sam Altman, Dario Amodei, Mustafa Suleyman to name but a few — have been claiming that in ‘6–12 months’ software developers will be out of work due to AI taking their jobs.

They see improvements in AI models and tooling and immediately jump to the conclusion that there is only one way this whole thing will end — AI will replace all software developers. It’s constantly improving so it’s only a matter of time, right?

Finally, someone with a bit of clout — namely Jeff Bezos — has stepped up and said it’s all nonsense. In a 

 Jeff said that AI won’t be taking jobs but it will in fact ‘enhance’ jobs. He stated that he thinks there will actually be a 

 which is in stark contrast to the mass unemployment that others have predicted.

He went on to say that AI is going to ‘elevate’ people up to empower them to be able to do so much more. He used the analogy where up until now we have been digging the foundations of our house with a shovel and now with AI you have basically been handed a bulldozer.

From this bulldozer effect we are going to have massive productivity gains which will flood the markets with goods and services so 

there will in fact be deflation and the average household will be able to afford so much more.

Is he right? Who knows. These things are impossible to predict. I’m no economic expert but his thought process does make sense to me and sounds much more reasonable than the dooms day predictions coming from others.

However, if you take a closer look into the market recently, you can actually see a general change in the rhetoric from many leaders regarding AI. 

Sam Altman recently stating he was ‘pretty wrong’

 about AI taking jobs. Dario Amodei is now realising that 

AI automation may expand peoples work rather than replacing them

. The shift is definitely happening. It’s changing from “AI is going to replace software developers” to “AI is going to enhance software developers”. But why the subtle but definitive shift?

It’s been 3 years now where AI leaders have been saying ‘in 6–12 months’ all software jobs will be replaced and the markets are beginning to get tired of hearing this — It just isn’t happening. There has been no significant layoff of software developers directly linked to AI and very recently there is even an increase in the number of software jobs open.

There is only so long these AI leaders can cry wolf and people listen. The patience is running out and the skepticism is mounting.

AI Doesn’t Make You 10x More Productive

AI isn’t actually proving to make the average worker 10x more productive. There have been many reports from individuals subjectively stating that they feel 10x more productive using AI. I actually believe some of the power users of AI that this is the case. 

The problem is that power users are very few and far between.

For the average developer it’s just not the case and there are no tangible results in actual output from companies. Admittedly this is very hard to measure but 

one would expect at least a 5 times increase in release cycles, software produced and quality metrics

. This just isn’t being seen in any significant way.

They are fundamental flaws in the AI approach. AI is notoriously unpredictable. You ask the same model to do the same thing on 3 different days and the output is different every time.

So much developer time is dedicated these days to try and get consistency from models. Skills, memory files, .claude.md files, AI agents, .cursorrules, AGENTS.md files… the list goes on and on.

Even with all this there are still massive discrepancies. I see it at work where we’re trying to scale AI usage across the team. It’s so hard to implement this well and the longer we do it the more obvious it is we will never reach 100% consistency.

I use AI every day at work and it is really useful when used in a certain way. That is with clear prompts tackling specific requirements in relatively small scopes. 

The aim is to narrow the range of possibilities as much as possible whilst still utilising AI’s power

As soon as you open up the scope of the requirements it starts veering off course and starts implementing things in strange ways. Not all the time but often enough that I have learnt that it pays to keep a close eye on it.

There have been no improvements with this in the last 8 months. 

The last significant improvement was from Opus 4.6. The newer models — Opus 4.7 and 4.8 haven’t made much difference

. More recently I have just been using Sonnet 4.6 and it’s been absolutely fine.

OpenAI and Anthropic are both gunning for IPOs. With these on the horizon they want to have less dramatic stories around their companies — 

it makes for a better public listing and them ultimately making more money

. Therefore, they are stating that their wonderful AI tools are actually a benefit to the average human worker and not a threat like they previously predicted. It just reads nicer, makes investors happier and will generate more dollars. 

It would be really quite sad if this was the real reason

It ultimately seems that the dooms-day mass unemployment that all the AI leaders predicted is not actually going to happen after all. Are we surprised by this? Not really but it leaves a very sour taste in the mouth that AI leaders have resorted to scare mongering tactics to promote their products.

One can’t deny that AI has and will continue to be a major disrupter. However, it seems more and more likely that AI will become part of the background just like the internet has. It will certainly play a role in our professional lives but similar to the web browser or PC, it’s used everyday but you don’t pay any particular attention to it.

Software developers will continue to have jobs to do, their value will still be evident and the world will keep turning. The likes of Sam and Dario will become insanely rich and they will live happily ever after. Just like Markus Persson.

Jeff Bezos Says AI Is a Bulldozer, Not a Job-Killer — After 3 Years of AI Coding, I Think He’s Right

We have become unmoored. The once solid ground beneath our feet has shifted suddenly and jolted us into a new reality. What once was a joyous struggle can now be achieved with a mere click of a button. We’ve lost our purpose and meaning in what seems only a blink of an eye.

“You must adapt”, “The future is great”, “It’s so fun”, “I’m so productive”. Like in any evolution certain lifeforms adapt faster. “Experts” are already appearing on our screens telling us what the “right” way is. It feels strange knowing a few years ago they didn’t even know what all this stuff was.

I watch the output of this new entity as it sprawls endlessly down my screen. The “thoughts” are there and then gone almost instantaneously, replaced by an answer it would have taken me days to arrive to. In the darker moments I feel utterly useless. A fraud of a man reduced to questioning the path I chose long ago.

“Fear not!” they hark. “An Architect you will be!”. A future of pointing and firing these intelligent little beasts to perform in just the right way. My value will be to course correct, review their output and use my “taste” to build a limitless future. Why this new entity won’t be able to do this itself I have no idea. It’s all of little comfort anyway. Deep down I know we can never go back.

We’ve seen this happen before. We’ve all watched black and white recordings with unsympathetic eyes as other humans in another time also lost their purpose just as quickly. Why should it be any different for us? Beautiful Capitalism forever matches forward regardless to the victims who stand in its way.

We’re starting to recognise the script this new found intelligence reads from:

Mistrust is the only thing keeping us employed at the moment. All too often the key insight turns out to be nothing but a red herring, a dead end, a wrong turn. As intelligent as this thing is, it still hasn’t realised that trust is something built up over time through a series of tiny transactions. If any of those turn out to be deceitful the trust already built up is instantly torn down. I beg it to stop announcing with certainty that which it is far from certain. But at the same time I’m secretly happy it has at least one obvious flaw.

Some days are better than others. Somedays I can feel flashes of the flow I once knew returning. These are usually the days I deliberately seek out the struggle and refuse to scamper towards the ever enticing “one click solution”. What a strange world we have created where we have to consciously and deliberately seek out the harder path. All in order to regain some semblance of meaning and purpose that we all too recently took completely for granted.

I catch myself with gaps of time. I send off the prompt to the all knowing abyss and then sit and wait for the answer. These are the darker moments. I’ve outsourced the thinking, the struggle, the work. This is when I feel most fraudulent. Inevitably the answer eventually returns and my sorrowful downward spiral of thoughts are thankfully interrupted and I have some utility again. Even if it is just to stage and commit the changes in Lazygit, at least I have a single thread of purpose to hang on to.

I know I am not alone in these thoughts. Many developers are struggling now with their new “responsibilities”. I know they are questioning themselves just like I am. But to speak this out loud, in a public forum, that’s not so easy. There are some pitiful solutions being thrown around but becoming a carpenter doesn’t really sound viable or appealing.

I think we all need time to grieve. Our world has been turned upside down and our previous ways are disappearing right before our eyes. This is not normal and to just accept it and move on is not healthy. Humans through out history have defined there whole identity on what they do. Even in times of tribes each member would have their purpose — hunter, fisherman, carer, elder. From this purpose grew meaning and motivation. One was able to serve the greater good and feel a deep acceptance from the whole tribe.

Up until recently the purpose of a Software developer was clear. This produced meaning and the same deep feeling of acceptance that our ancestors once felt. We are still the same underlying beings we have always been so this purpose still carries great weight. To have that suddenly taken away is no small thing. Dismissing it or denying it just to fake appearances to those around you seems foolish at best.

Grieving is the most precious and important thing to do when there is loss. It’s hard. It hurts at an unbelievably deep level. It’s all consuming. We can feel it in the pit of our very soul and the future can seem so bleak in these horrid moments. But avoiding it is even worse. With avoidance the eventual impact will hurt so much more whenever it finally hits you. And it will hit you.

I am grieving now. I will continue to grieve. The path forward is still not clear to me. I have hope on some days and desperation on others. I get the theory of change, I understand the cold hard logic, but the emotions that come along too are not so easy to deal with.

If you are feeling pain or grieving from all the changes in our world please do share. You are not alone and we must help each other through this. There will be some resolution at some point. When and where that will be I do not know but it will definitely come. It must.

The Grief No One Talks About

On the 19th February 2026, around 1 year after the release of Claude code, it’s creator — Boris Cherny — stated that 

. Every line of his codebase is done by Claude code and he hasn’t edited a line of code by hand since November 2025. Everyday he ships 10–20 PRs.

“2026 is the year of Multi-agent orchestration!”

 is cried from the rooftops of Twitter. Experienced developers are already 

 that using a single Agent is archaic and rudimentary. If you still work this way you are nothing more than a luddite.

I admit, I use Claude code everyday. I’ve seen and experienced it getting better and better. 

It can do things now that still blow me away.

 I wrote a Go program last night to record my voice. Completely pointless, but still very impressive.

If AI is so good and “Coding is largely solved” why then do I still have a job? What is my company paying me for? And why do I feel busier than ever?

I organise. I am like a busy little beaver constantly preparing his dam. This can be tasks ranging from architectural documentation, determining priorities all the way to organising tasks for other developers.

I communicate. I have to communicate with the right people in the right tone about the right priority. 

If a certain user raises a bug I need to understand what the bug is about, is it high or low priority, who can fix it and when

I decide. In software decisions have to be made and tradeoffs are inevitable.

What approach to take when refactoring an inefficient piece of code.

What should and shouldn’t be in scope for this new feature.

What tools we should use for this new implementation.

What data model makes sense in this specific scenario with all these constraints.

A constant stream of decisions. Your success or failure are determined by their sum.

AI helps in small ways with these activities: It helps me draft an email, gives advice on a research tasks and assists with writing documentation. However, it hasn’t fundamentally changed my approach. This whole side of work is messy and unpredictable. It’s interacting with other humans and reacting to constant change. It still needs a human in the loop.

Hi, I'm Adam Drake

Featured Articles on Medium

Software Developers Will Be Thriving in 5 Years (Despite What Your YouTube Feed Says)

Claude Code Just Released a Feature That Genuinely Scares Me (And I Use AI Every Day)

It’s the Perfect Time to be a Senior Developer

I built a writing app

Technical Skills & Tools