ai

Finally! I’ve been waiting for this since forever.

Automatic Git commit messages are finally here in Windsurf — just one of the many amazing new AI features they’ve added in the new Wave 6 update that I’ll show you.

Incredible one-click deployment from your IDE, intelligent memory… these are huge jumps forward in Windsurf’s software dev capabilities.

1. One-click deployment with Netlify — super easy now

Okay this is a game changer.

They’ve teamed up with Netlify so you can literally deploy your front-end stuff with just one click right from Windsurf.

Literally no context switching. Everything stays in your editor.

Here we’re claiming the deployment to associating it with our Netlify account.

No more messing with all those settings and manual uploads.

With Wave 6 you just build your app, tell Windsurf to deploy, and it’s live instantly.

Just imagine the flow: you whip up a quick landing page with HTML, CSS, and JavaScript and instantly you reveal it to the world without even switching from your browser.

Your productivity and QOL just went up with this for real.

2. Conversation table of contents

Quickly jump back to earlier suggestions or code versions.

Super handy for those longer coding chat sessions.

3. Better Tab

They’ve upgraded Windsurf Tab inline suggestions once again to work with even more context.

Now it remembers what you searched for to give you even smarter suggestions.

And it works with Jupyter notebook now too:

4. Smarter memory

Windsurf already remembers past stuff but they’ve made it even better.

Now you can easily search, edit, and manage what it remembers — so you have more control over how the AI understands your project and what you like.

5. Automatic commit messages

Yes like I was saying — Windsurf can now write your Git commit messages for you based on the code changes.

One click, and it gives you a decent summary. Saves a bunch of time and helps keep your commit history clean.

6. Better MCP support

If you’re working in a bigger company, they’ve improved how Windsurf works with those Managed Code Providers.

7. New icons and much more

Just a little update among others — they’ve got some new Windsurf icons for you to personalize things up.

Also the ability to edit suggested terminal commands and much more.

This new one-click deployment could really shake things up for front-end development. — making getting your work out there so much faster and lets you focus on the actual coding.

As AI keeps getting better, tools like Windsurf are going to become even more important in how we build software.

Wave 6 shows they’re serious about making things simpler and giving developers smart tools to be more productive and creative. This new update could be a real game changer for AI-assisted development.

GPT-4o’s new image generation is destroying industries in real-time.

Not even up to a week and it’s been absolutely insane — even Sam Altman can’t understand what’s going on right now.

Things are definitely not looking too good for apps like Photoshop.

Look how amazing the layering is. Notice the before & after — it didn’t just copy and paste the girl image onto the room image, like Photoshop would do.

It’s no longer sending prompts to DALL-E behind-the-scenes — it understands the images at a deep level.

Notice how the 3d angle and lighting in the after image is slightly different — it knows it’s the same room. And the same thing for the girl image.

These are not just a bunch of pixels or a simple internal text representation to GPT-4o. It “understands” what it’s seeing.

So of course refining images is going to so much more accurate and precise now.

The prompt adherence and creativity is insane.

What are the odds that something even remotely close to this was in the training data?

It’s not just spitting out something it’s seen before — not like it ever really was like some claimed. How much it understands your prompt has improved drastically.

And yes it can now draw a full glass of wine now.

Another huge huge upgrade is how insanely good it is at understanding & generating text now.

This edit right here is incredible on so many levels…

1. Understanding the images well enough to recreate them so accurately in a completely different image style with facial expressions.

2. It understand the entire context of the comic conversation well enough to create matching body language.
Notice how the 4th girl now has her left hand pointing — which matches the fact that she’s ordering something from the bar boy.
A gesture that arguably matches the situation even better than in the previous image.
And I bet it would be able to replicate her original hand placement if the prompt explicitly asked it to.

3. And then the text generation — this is something AI image generators have been struggling with since forever — and now see how easily GPT-4o recreated the text in the bubbles.

And not only that — notice how the last girl’s speech bubble now has an exclamation point — to perfect match her facial expression and this particular situation.

And yes it can integrate text directly into images too — perfect for posters & social media graphics.

If this isn’t a total disruptor in the realm of graphics design and photoshopping and everything to do with image creation, then you better tell me what is.

It’s really exciting and that’s why we’ve been seeing so many of this type of images flood the social media — images in the style of the creative studio, Ghibli.

And also part of why they’ve had to limit to only paid ChatGPT users with support for the free tier coming soon.

They’ve got to scale the technology and make sure everyone has a smooth experience.

All in all GPT-4o image gen is a major step forward that looks set to deal a major blow to traditional image editing & graphic design tool like Photoshop & illustrator.

Greater things are coming.

Amazon’s new Q Developer could seriously change the way developers write code.

It’s a generative AI–powered assistant designed to take a lot of the busywork out of building software.

A formidable agentic rival to GitHub Copilot & Windsurf, but with a special AWS flavor baked in — because you know, Amazon…

It doesn’t matter whether you’re writing new features or working through legacy code.

Q Developer is built to help you move faster—and smarter with the power of AWS.

I see they’re really pushing this AWS integration angle — possibly to differentiate themselves from the already established alternatives like Cursor.

Real-time code suggestions as you type — simply expected at this point, right?

It can generate anything from a quick line to an entire function — all based on your comments and existing code. And it supports over 25 languages—so whether you’re in Python, Java, or JavaScript, you’re covered.

Q Developer has autonomous agents just like Windsurf — to handle full-blown tasks like implementing a feature, writing documentation, or even bootstrapping a whole project.

It actually analyzes your codebase, comes up with a plan, and starts executing it across multiple files.

It’s not just autocomplete. It’s “get-this-done-for-me” level AI.

I know some of the Java devs among you are still using Java 8, but Q Developer can help you upgrade to Java 17 automatically.

You basically point it at your legacy mess—and it starts cleaning autonomously.

It even supports transforming Windows-based .NET apps into their Linux equivalent.

And it works for the popular IDEs like VS Code — and probably Cursor & Windsurf too — tho I wonder if it would interfere with their built-in AI features.

• VS Code, IntelliJ, Visual Studio – Get code suggestions, inline chats, and security checks right inside your IDE.
• Command Line – Type natural language commands in your terminal, and the CLI agent will read/write files, call APIs, run bash commands, and generate code.
• AWS Console – Q is also built into the AWS Console, including the mobile app, so you can manage services or troubleshoot errors with just a few words.

Q Developer helps you figure out your AWS setup with plain English. Wondering why a network isn’t connecting? Need to choose the right EC2 instance? Q can guide you through that, spot issues, and suggest fixes—all without digging through endless docs.

Worried about privacy? Q Developer Pro keeps your data private and doesn’t use your code to train models for others. It also works within your AWS IAM roles to personalize results while keeping access secure.

On top of that it helps you write unit tests + optimize performance + catch security vulnerabilities—with suggestions for fixing them right away.

Amazon Q Developer isn’t just another code assistant. It’s a full-blown AI teammate.

It’s definitely worth checking out — especially if you’re deep in the AWS ecosystem.

Never underestimate Google!

The new Gemini 2.5 Pro model just changed everything in the AI race.

Look at what it created with just a few sentences of prompt:

Google is no longer playing catch-up in the LLM race. They’re ahead now.

After many of you had been looking down on Gemini for so long, now look…

Back to the #1 spot they undisputedly were only a few years ago, before what happened in 2022.

Not like Gemini 2.0 was even bad, but this is a massive massive step-up from that.

Reason, math, coding… it’s either better or seriously competing with the others at almost everything.

Everybody was praising Grok just a while ago but this Gemini 2.5 has already surpassed it in major areas.

1 million context window and 2 million coming very soon — and as always with multimodal processing for text, images, audio, and video…

Complex multi-step thinking is here…

Look at a puzzle someone used to find out just how good this new model is:

How many of us can even figure out this pattern in less than a minute?

This is complex reasoning stuff that would destroy regular models like GPT 4.5 — but Gemini took just 15 seconds to figure this out. Correctly.

Meanwhile rivals like Claude 3.7 Thinking and Grok spent well over a minute before they could get the answer.

At this point we’ve now clearly got beyond the traditional next-token prediction models — already “traditional” in 2025.

It’s also apparently insanely good at generative the perfect SVG icon for you with high precision.

And all this for immensely generous prices.

In OpenAI Playground you pay for token usage — completely free in Gemini AI Studio.

And there’s still a free trial for actual API usage.

The paid tier is already looking like it would be much cheaper than OpenAI’s o3-mini — and lightyears cheaper than the o3 monster.

Gemini 2.0 is already around 10 times cheaper than o3-mini and I doubt 2.5 would have a price that would be significantly higher.

With everything we’ve been seing in recent months it’s just so clear that OpenAI is no longer miles ahead of the rest anymore.

They will never again get the sort of undisputed dominance they got when ChatGPT first came out.

Now Google’s showing us that they were never really out — and unlike OpenAI they won’t be struggling nearly as much with losses and fundraising. Whatever losses from AI gets massively offset with the avalanche of billions from Ad money.

Way easier for them to keep prices ridiculously cheap and generous like they’ve been doing. A massive long-term financial advantage.

The relatively underwhelming release of GPT 4.5 also didn’t help matters for OpenAI. Maybe it was even supposed to be the ultimate GPT 5, but it would have a massive failure to call it that.

Once again we continue to see the shift from “raw” LLMs to thinking agents with chain-of-thought prompting.

Google is back, Gemini 2.5 is fast, and once again a major change in the dynamics of the AI race.

Redefining what’s possible and setting new expectations for the future.

His AI bot made thousands of job applications automatically while he slept — only for him to wake up an interview request in the morning.

Over the course of 1 month he got dozens of job interviews — over 50.

And of course he’s not the only one — we now have several services out there that can do this.

But we can build it ourselves and start getting interviews on autopilot.

Looking at this demo already confirms my expectation that the service would be best as a browser extension.

No not best — the only way it can work.

Lol of course no way LinkedIn’s gonna let you get all that juicy job data with a public API.

So scraping and web automation is the only way.

So now if we want to set it up for LinkedIn like it is here.

Of course we can just go ahead and start the automation — we need some important input.

Looking at the input and their data types

Skills — list of text so string array/list

Job location — string of course, even though they could be an geolocation feature to automate this away.

Number of jobs to apply — too easy

Experience level and job type – string

If I’m building my own personal bot then I can just use hardcoded variables for all these instead of creating a full-blown UI.

So once you click the button it’s going to go straight to a LinkedIn URL from the Chrome extension page

Look at the URL format:

JavaScriptCopied!

linkedin.com/jobs/search/?f_AL=true&keywords=product%20management%20&f_JT=F&start=0

So it’s using some basic string interpolation to search the LinkedIn Jobs page with one of the skills from the input.

And we can rapidly go through the list with start query that paginates the items

And now this is where we start the web scraping.

We’d need to start parsing the list and items to get useful information for our application goals.

Like looking for jobs with low applications to boost our chances.

You can get a selector for the list first.

JavaScriptCopied!

const listEl = document.querySelector('.scaffold-layout__list');

Now we’d need selectors to uniquely identify a particular list item.

So each list item is going to be a <li> in the <ul> in the .scaffold-layout__list list.

And we can use the data-occludable-job-id attribute as the unique identifier.

Now we can process this li to get info on the job from the list item.

JavaScriptCopied!

const listEl = document.querySelector(
  ".scaffold-layout__list ul"
);

const listItems = listEl.children;

for (const item of listItems) {
  // ...
}

Like to find jobs that have that “Be an early applicant” stuff:

JavaScriptCopied!

for (const item of listItems) {
  const isEarlyApplicant = item.textContent.includes(
    "Be an early applicant"
  );
}

Also crucial to only find jobs with “Easy Apply” that let us apply directly on LinkedIn instead of a custom site, so we can have a consistent UI for automation.

JavaScriptCopied!

for (const item of listItems) {
  // ...
  const isEasyApply = item.textContent.includes("Easy Apply");
}

We can keep querying like this for whatever specific thing we’re looking for.

And when it matches we click to go ahead with applying.

JavaScriptCopied!

for (const item of listItems) {
  // ...
  if (isEarlyApplicant && isEasyApply) {
    item.click();
  }
}

Find a selector for the Easy Apply button to auto-click:

JavaScriptCopied!

for (const item of listItems) {
  // ...
  if (isEarlyApplicant && isEasyApply) {
    item.click();
    const easyApplyButton = document.querySelector(
      "button[data-live-test-job-apply-button]"
    );
    // delay here with setTimeout or something
    easyApplyButton.click();
  }
}

Do the same for the Next button here:

And then again.

Now in this late stage things get a bit more interesting.

How would we automate this?

The questions are not all from a pre-existing list — they could be anything.

And looks like service I’ve been showing demos of didn’t even do this step properly — it just put in default values — 0 years of experience for everything — like really?

Using an LLM would be a great idea — for each field I’ll extract the question and the expected answer format and give this to the LLM.

So that means I’ll also need to provide resume-ish data to the LLM — so

I’ll use our normal UI inspection to get the title.

JavaScriptCopied!

function processFreeformFields() {
  const modal = document.querySelector(
    ".jobs-easy-apply-modal"
  );
  const fieldset = modal.querySelector(
    "fieldset[data-test-form-builder-radio-button-form-component]"
  );
  const questionEl = fieldset.querySelector(
    "span[data-test-form-builder-radio-button-form-component__title] span"
  );
  const question = questionEl.textContent;
}

JavaScriptCopied!

function processFreeformFields() {
  // ...

  const options = fieldset.querySelectorAll(
    "div[data-test-text-selectable-option]"
  );
  const labels = [];
  for (const option of options) {
    labels.push(option.textContent);
  }
}

Now we have all the data for the LLM:

JavaScriptCopied!

async function processFreeformFields() {
  // ...
  const questionEl = fieldset.querySelector(
    "span[data-test-form-builder-radio-button-form-component__title] span"
  );
  const question = questionEl.textContent;

  const options = fieldset.querySelectorAll(
    "div[data-test-text-selectable-option]"
  );
  const labels = [];
  for (const option of options) {
    labels.push(option.textContent);
  }

  const { answers } = await sendQuestionsToLLM([
    { question, options: labels, type: "select" },
  ]);
  const answer = answers[0];
  const answerIndex = labels.indexOf(answer);
  const option = options[answerIndex];
  option?.click();
}

So we can do something like this for all the fields to populate the input object we’ll send to the LLM in the prompt.

And with this all that’s left is clicking the button to submit the application

I could also do some parsing to detect when this success dialog shows.

I could use a JavaScript API like Mutation Observer to detect when this element’s visibility property changes — like the display property changing from 'none' to 'block'.

But with this I’d have successfully auto-applied for the job and I can move on to the next item in the jobs list.

JavaScriptCopied!

const listEl = document.querySelector(
  ".scaffold-layout__list ul"
);

const listItems = listEl.children;

for (const item of listItems) {
  // ...
}

Or the next page of jobs

JavaScriptCopied!

const page = 1;
// 0 -> 25 to go to next page
const nextPage = `linkedin.com/jobs/search/?f_AL=true&keywords=${skills[0]}&f_JT=F&start=${page * 25}`

This new IDE from Google is seriously revolutionary.

Project IDX is in a completely different league from competitors like VS Code or Cursor or whatever.

It’s a modern IDE in the cloud — packed with AI features.

I was not surprised to see this sort of thing coming from Google — with their deep-seated hatred for local desktop apps.

Loading your projects from GitHub and then install dependencies instantly without any local downloading.

It’s a serious game changer if your local-based IDE is hoarding all your resources in your normie PC — like VS Code does a lot.

Tari for the last time, VS Code is a code editor and not an IDE!! Learn the difference for goodness sake!!!

Ah yes, a code editor that eats up several gigabytes of RAM and gobbles up all your battery life that your OS itself starts complaining bitterly.

Such a lightweight code editor.

Most certainly not an IDE.

Anyway, so I could really see the difference between VS Code and IDX in my past PC.

Like when it came to indexing files in a big project, to enable language features like Intellisense & variable rename.

VS Code would sometimes take forever to load and it might not even load fully — bug?

I would have to reload the window multiple times for the editor to finally get it right.

But with IDX it was amazing. The difference was clear.

Once I loaded the project I had the all the features ready. Everything happened instantly.

Because all the processing was no longer happening in a weak everyday PC but now in a massively powerful data center with unbelievable speeds.

Having a remote server take care of the heavy lifting drastically cuts down on the work your local PC has to handle.

Including for project debugging that take lots of resources — like Android Emulator tests.

The Android Studio Emulator couldn’t even run in my past PC without crashing miserably, so seeing the IDX emulator spring into life effortlessly with near-zero delay was pretty exciting.

Templates are another awesome convenience — just start up any project with all the boilerplate you need — you don’t even need to fire up the CLI.

And no you’re stuck with those templates there — you can just start from a blank template and customize it as much as you want — like you would in local editors.

Another huge part of IDX is AI of course — but lol don’t think they’ll let you choose between models like all those others.

It’s Gemini or nothing. Take it or leave it.

Not like it’s nearly as bad as some people say — or bad at all.

And look, it indexes your code to give you responses from all the files in the codebase — something that’s becoming a standard feature you’d expect across editors.

And it looks like it has some decent multi-step agentic AI editing features.

I was impressed — It tried creating the React app and it failed because there were already files in the folder — then see what happened…

It intelligently knew that it should delete all the files in the project and then try again.

It automatically handled a failure case that I didn’t tell it about beforehand and got back on track.

And guess what?

After it tried deleting the files and it didn’t work — cause I guess .idx can’t be deleted — it then decided to create an empty subfolder to create the React project in.

I never said anything about what to do about non-empty files in the folder in this case, it just knew. It didn’t keep trying blindly for something that just wasn’t working.

Pretty impressive.

Okay but it did fail partially miserably when it came to create the React file.

It put the CSS code in the JSX file where it was obviously not supposed to be.

So clearly whatever model they’re using for this still can’t compare to Claude. Cause Claude-powered Windsurf would never make this mistake.

But not like the CSS itself was bad.

But of course this will only continue to improve. And Clause will also get even better — as you might have seen from the recent Claude 3.7 release.

So even if you stick with your local IDE, IDX is still a solid, rapidly improving, AI-powered alternative for writing code faster than ever.

AI is slowly taking over coding but many programmers are still sticking their head in the sand about what’s coming…

Now Google’s Chief Scientist just made a telling revelation: AI now generates at least 25% of their code.

Can you see — it’s happening now at top software companies with billions of active lines of code.

All these people still acting like AI-assisted coding is just a gimmick that nobody actually uses in production.

Some people in my comment sections even said that using AI tools don’t make you more productive…

Like come on — I thought we all agreed GitHub Copilot was a smash. The over 1.3 million paying users they had this time last year wasn’t enough proof?

In case you don’t know, software developers are not a very easy group of people to monetize — your tool must be really something to have over 1.3 million of them pay for it.

And even if most of these are from businesses, something tells me not every developer tool can get anywhere close to these numbers from B2B.

I remember the first time I used Copilot. Mhmm nice tool, pretty decent suggestions, not bad…

Only like a few days later when I had to code without it from connection issues — that’s when I realized just how much I’d already started depending on this tool. I was already getting used to the higher quality of life and I wasn’t even fully aware.

That Tab key for accepting completions — which key did I even press more between Tab and semicolon.

• Type 48 characters — Enter
• Type 60 characters — Enter
• Type 55 characters — Enter

After:

• Type 9 characters — Tab — Enter
• Type 2 characters — Tab — Enter
• Tab — Enter

The quality of life difference was undeniable. The productivity difference was undeniable.

And one thing this shows you or reminds you — that programming has always been an act of thinking, not typing.

It’s always been the thinking part that took most of the time — the higher level system planning and designing, the lower level algorithms and design patterns.

The typing has always been straightforward. And pretty mundane actually.

Copilot isn’t just a code completion tool, it’s a thought predicting tool.

It’s not just about helping you code faster, it’s about knowing what you’re thinking and eliminating the gap between that thought and its actualization in the real world. Pressing Tab instead of dozens of characters.

It’s been so useful and this is just at the lower line-by-line level — predicting your thoughts for what each line should be.

Now we are having tools like Supercomplete predicting your intent across entire files, making things even easier.

Cursor Compose and Windsurf Cascade bringing your thoughts to life across several files in your codebase.

And there are increasingly magnifying the impact and value of those thoughts.

Let’s say you want to add a searching feature to your web app.

Copilot could give you completions for each line of the UI components + event handler definition and the search algorithm or external libraries you decide to use.

Supercomplete could automatically create an empty event handler for you to start writing the definition.

But with the agentic tools you could just say, “add a search feature to the app”, and it could handle everything — all the above — including NPM library installations.

How long until you can literally say, “build and deploy an e-commerce app…” and that’ll be all it takes?

Imagine you give such a vague description of what you want and then the AI autonomously asks you questions to get the specific requirements and avoid all ambiguity.

It seems more and more like a matter of when, not if.

Adobe just changed everything for AI video generation.

Their new Firefly video model is finally here and it already has insane advantages over Sora and even Veo 2.

This is insane.

Like you’re telling me this wasn’t taken by some National Geographic photographer. This actually came from an AI.

So where exactly are we going to be a year from now?

I agree with Scarlett Johansson (lol) — we should really do something about deepfakes before it gets out of hand.

But only if we can pretend like there’s any going back from this — which there isn’t…

Massive misinformation is on its way — already here as we saw from the fake AI video of celebrities protesting against Kanye West.

At this rate soon video evidence won’t be able to hold up in court — they’ll just say it’s a deepfake right? Who would know? It’s already happening for audio, right?

With this new update Adobe now has video + image + vector generation all in the same app — genius move to gain an upper hand in this part of the AI race.

They know that the value of an AI tool isn’t just in how good it is — but how deeply integrated it is into a workflow that convenient and familiar.

Even if other tools like Sora produce slightly better videos, the deep integration of all their creating tools will still give them a major advantage.

With one ecosystem you can generate images… then edit them yourself… or with the AI…

Then transform the image into dynamic videos and scenes… Then create audio for the scenes from text…

Then translate the audio in the scenes to several other languages — syncing the lips perfectly (wild stuff).

Then you can still create fresh videos from scratch with text prompts giving you precise control over the style and camera angles…

And you can still edit them yourself for total precision…

The integration is simply unbeatable — and they already have a strong user base of many millions.

Everything is so connected and cohesive from conception to production.

And they realize this and so they tie everything together with Firefly in their Creative Cloud subscription.

And of course you’ve still got the standalone subscription for general users, so they still compete directly with Sora and Veo 2.

And once again they claim to have only used “licensed” and “public domain” content for the training, just like the did for the image generation model.

Of course hardly anyone is going to care about this when choosing tools, ha ha.

But I guess it’s a nice way to virtue signal and appear morally superior to lawsuit-ridden rivals like Midjourney and OpenAI, lol.

It’ll just be really interesting to see how good these tools are gonna get.

Imagine: complete hyper-realistic, engaging, comprehensive 2-hour long movies from a few paragraphs of prompts.

So we won’t be just imagining…