Narciss

Yeah just saw that, I'm gonna keep converting it in my head.

Le Chaton Fat is here!

Can't apply, but I love your product

In the eternal words of John Oliver: Cool

Exactly. If you try to understand, really strive to understand what the AI is producing, then a lot of these arguments fall flat.

I exaggerated. But I'm so deep into these things that it's like someone writing emphatically 'colours don't exist,' or 'toenails don't grow on their own.' (Dunno why I thought of this second example)

My GF says I have neither.

My AI discovered this days ago when I wanted to deploy a new vibe coded website (it was to keep score while playing whist and rentz)

Thought it was very cool

Woaaah buddy this is such a wrong statement that I’d delete it if I were you.

Can’t believe that people confidently spew blatantly false statements like this.

Skills matter, a lot, to every action that requires the AI to find stuff out, so that it doesn’t have to find the same stuff out again. Operating a website, building PowerPoints the way you like them, operating across different surfaces like APIs + GUIs…otherwise the AI has to relearn how to do it every time.

Be confident about things you know. Study about things you don’t.

I’d recommend making it responsive, the bottom bar for example has a lot of overlapping elements on my phone

Curious what you think of sentienttube.com

I’ve built it as a side project, and the cost to produce one 20-40 minute video is in the 5$ range.

My friends/family have watched some of the better videos. All one shotted, and the storylines come out surprisingly well.

Currently working on a new engine that generates video, but it’s expensivee

Open to collabing

I have no idea how you could try and hold this argument without being facetious.

Many improvements have come to AI that have reduced costs of inference and training, like sparse attention, and many more will arise in the future. To talk about the cost of AI right now versus the future is to talk about the first IBM computers versus the personal computing that appeared years later. The cost will go down. In fact that is what the major labs are definitely banking on.

I can’t believe that anyone would actually think this. This

Nah it’s all from the pretraining data

Interesting

This is a great article, thanks for sharing

hmm didn't get the pun...Time to turn to chatGPT :))

Definitely didn't want to imply that the author is a bad engineer, quite the contrary he seems like a very good one. Apologies if it came across that way.

Just that many brilliant engineers as themselves test agentic tools without the same level of thorough understanding that they give to other software engineering tools that they test out.

That was a different matter altogether. I agree though that I didn't touch on that.

My experience is different in that case, but it certainly depends on the type of technical challenge, the programming language, etc.

Candidates that perform better or worse exist with and without agentic coding tools. I've had positive and negative experience on both fronts, so I'd attribute the OP's experience to the N=1 problem, and perhaps to the model's jagged intelligence.

I work mostly in Typescript, and it's well known that models are particulary well versed in it. I know that other programming languages are less supported because the training data for them is lower, in which case models could be worse with them across the board (or some SOTA models could be better than others)

I did a bit of digging into why you think agentic coding is “not there yet”, and I think you are bashing a tool you have very little experience with and are using a bit wrongly.

Nothing wrong with that, except that as opposed to any other tool that is out there, agentic coding is approached by smart senior engineers that would otherwise spend time reading documentation and understanding a new package/tool/framework before giving conclusions around it with “I spun up Claude code and it’s not working”. Dunno why the same level of diligence isn’t applied to agentic coding as well.

First question that I always have to such engineers is “what model have you tried?” And it always ends up being the non-SOTA models for tasks that are not simple. Have you tried Claude Opus?

Second question: have you tried plan mode?

And then I politely ask them to read some documentation on using these tools, because the simplicity of the chat interface is deceptive.

Fanvue | AI Internal Developer Tooling Engineer | REMOTE (London based, GMT-5 to GMT+5 preferred) | Full-time

One of the coolest roles we've had: experiment with cutting-edge AI tools to make talented engineers faster and more effective. Hands-on, experimental, operating at the frontier.

Fanvue is a fast-growing creator monetisation platform — AI-powered, creator-first (Series A, $100M+ ARR, triple-digit YoY growth), supporting hundreds of thousands of creators and millions of fans.

What you'll do: Define and roll out our AI-assisted dev stack (Cursor, Claude Code, etc.) across IDEs, PR workflows, and CI. Build MCP servers and AI-ready infra for context-aware code generation. Enable parallelised workflows, agent skills, and AI-assisted reviews. Establish best practices for safe, consistent AI-assisted coding. Track and report measurable impact. Evaluate emerging tools with clear success criteria.

Who you are: Strong software engineering background with TypeScript in production. Hands-on with AI coding tools (Cursor, Claude Code, Aider, Copilot). Experience with MCP servers. Solid LLM fundamentals (RAG, embeddings, fine-tuning). Comfortable with GitHub workflows and CI/CD. Autonomous, experimental, outcome-focused.

You'll thrive if you want to make engineers dramatically more effective, enjoy rapid experimentation, and own outcomes. You'll struggle if you prefer fixed roadmaps or need heavy direction.

Why Fanvue: Define responsible AI at scale, direct impact on velocity and quality, access to top AI tools, competitive salary, unlimited holiday, remote-first, flexible hours.

Apply: https://jobs.ashbyhq.com/fanvue.com/dcf1bcaf-a0af-4131-903c-...

Reference: Narcis Marincat

I opened it in the morning while my partner was sleeping next to me.

I see the big red “press me” button sitting in a corner, and when I pressed, a rich farting sound blasted out of my phone’s speakers, which coincidentally were on full volume. It was LOUD enough to hear it throughout the house.

My partner’s only reaction was to say “great” in a low voice :)))

Thanks for the laugh!

I’m all for building weird stuff. Unfortunately, I have absolutely no idea what this is so can’t use it, but it was fun to try and figure out.

No IT issues thank god! Some work on my side proj maybe to unwind.

Merry xmas everyone!

LOL

Context7 might be good for you

Here we go again....

It sounds like an API issue more than anything. I was working with it through cursor on a side project, and it did better than all previous models at following instructions, refactoring, and UI-wise it has some crazy skills.

What really impressed me was when I told it that I wanted a particular component’s UI to be cleaned up but I didn’t know how exactly, just wanted to use its deep design expertise to figure it out, and it came up with a UX that I would’ve never thought of and that was amazing.

Another important point is that the error rate for my session yesterday was significantly lower than when I’ve used any other model.

Today I will see how it does when I use it at work, where we have a massive codebase that has particular coding conventions. Curious how it does there.

I've been working with it, and so far it's been very impressive. Better than Opus in my feels, but I have to test more, it's super early days