martypitt

I 100% did not write this with an LLM. I've run out of tokens.

It's weird times.

I feel incredibly productive. I'm building in an afternoon what would've taken weeks. I spend all my time in either MR's reviewing code, or a terminal prompting.

I've moved from being a coder, to being a product-engineer-architect. I love coding -- LOVE it. But the role has morphed. And, I actually really like the new role. I love being product centric, and caring about architecture -- it suits me wel..

The code Claude produces is often clean, but terribly archictected. So I'm spending a lot of time reviewing in detail.

But the anxienty - OMG the anxiety.

I work on multple features (generally 4-5 work streams) concurrently, so am constantly context switching. I worry about how much time I'm spending on each task. Am I doing enough code review? Too much? Too little?

What about click-through testing? Our test coverage has never been higher - should I be able to just merge these features? Wasn't that always the promise of TDD - merging with confidence? But, it feels like a risk.

And, I'm moving really really fast - but I assume my competitors are too. So that drives me to move faster. Automate more. Use claude in more places. Which brings more anxiety - am I cutting too many corners? Is this all gonna crumble on me?

Also, is everything I'm working on going to become irrelevant? Will customers buy this product, or vibe code it? Do we even have a moat? Anxiety. More anxiety.

My investors are reading stuff constantly too. They're pinging me with market updates, emerging players, shifting landscapes. More anxiety. Also - productivity tools - look - internet influencer X is now producing a gajillion lines of code a second -- are we doing that? Are we token maxing? Are we feature maxing?

Are we building the right number of internal tools? Are we automating enough? Should I evaluate the market for this new tool, or just smash something out with claude? More features. Burn more tokens. Ship ship ship.

Having to explain to investors why we're not going as fast as those guys, and building enterprise products requires care and dedication -- that takes time. Time I should be shipping, coding, featuring, tokenizing. More anxiety.

I'm exhausted.

Anyway, gotta go - herdr has pinged me four times during writing this reply. Gotta ship.

I like the look of this - and it's a problem that we're thinking about right now at work.

But, the pricing of this is .. really high .. - starting at $5k / month? I'd find that difficult to justify.

This thread prompted me to go and find out what my first computer was -- I have vague memories of it.

Turns out, it was a Sega SC-3000H, back before Sega decided it was a console company. Also, interestingly, it was really only popular in NZ/Aus (I grew up in NZ).

I have very clear memories of spending hours copying BASIC code of games, line-by-line from the monthly Sega magazine into the BASIC editor, playing it for 15 minutes, then everything dissapearing when I restarted it.

I was always envious of my friend who had a C64, but that Sega was a great little machine.

Slightly OT - but what's the process for training an LLM to author a new language like this proficiently?

I ask because I have my own language I maintain, and we're currently prompt-stuffing to get LLM's to author it - but I wonder what type of training set you'd need, and what base image one would use to fine-tune a model, and how effective it'd be?

FYI - I tried visiting your site. In Chrome (tested in Incognito as well), I get a massive white space at the top, with a vertical scroll. If I scroll far enough, I see the site.

Worked fine in Firefox.

Any background / context around what the Chicory author means in this comment?

> We'll consider merging in changes that make sense from Endive, but under the stewardship of the [Byte Code Alliance] I have very little faith in its future. My words mean nothing though having all but completely lost interest and use for WebAssembly.

What's the background / history of Byte Code Alliance?

I wonder if they'll talk about AI?

I don't have any LSP's hooked up to CC yet (going to fix that today), or particularly sophisticated CLAUDE.md files.

So, if I've read this post correctly, that means that CC is navigating my codebase today by sending lots of it up to a model, and building an understanding. Is that correct? Did I misunderstand it?

I kinda suspected there was more local inference going on somehow -- partly because the iteration times are fairly fast.

Impressive benchmarks!

> Rebuilding Coinbase as an intelligence, with humans around the edge aligning it.

Oof. That smacks of hubris and valley-buzzwordism.

> Leaders will own much more, with as many as 15+ direct reports.

> Every leader at Coinbase must also be a strong and active individual contributor.

So, a manager who's managing 15 people AND expected to ship -- that sounds awful for both sides.

OT - but Bhatti looks really cool! Well done!

I can see you're A/B testing some different hero text.

I got:

> Write a config, not a conversation

Which I found let me wondering - "What is this thing?" I refreshed a few times to the variations, and while some were better, I feel like your hero could do with being less pithy, and more plain explanation of what it is.

For one, OpenScreen supports Linux, whereas Cap doesn't. I appreciate it's small minority that appeals to, it's just that I'm in it.

I've lived in London for a decade, and feel incredibly lucky to have access to the transit here - having lived in Aus, NZ and Canada previously.

It's not perfect. It's late sometimes, pollution sucks, and often crowded - but people here who like to criticise it really don't recognise how much better they have it than lots of other places.

Same with travel from here to Europe (by train), is just awesome.

This is a really great post - and what they've built here is very impressive.

I wonder if we're at the point where the cost of building and maintaining this yourselves (assisted with an AI Copilot) is now more effective than an off-the-shelf?

It feels like there's a LOT of moving parts here, but also it's deeply tailored to their own setup.

FWIW - I tried pointing Claude at the post and asking it to design an implementation, (like the post said to do) and it struggled - but perhaps I prompted it wrong.

Interestingly, Devin lists Ramp (the OP) as a customer on their front page.

Surprised they need both.

Dell have announced the return of XPS.

Fairly limited specs available so far, but more are coming, including a developer edition - which ships with Ubuntu 24.10.

Current configs are limited to 32GB of RAM, which is a little low, but hopefully that will increase with future iterations.

> ... the company which made the ad, defended its use of AI in a post on LinkedIn

> “It’s never about replacing craft, it’s about expanding the toolbox. The vision, the taste, the leadership … that will always be human,” she said.

> “And here’s the part people don’t see: the hours that went into this job far exceeded a traditional shoot. Ten people, five weeks, full-time.”

That response sounds like it was written by ChatGPT, which is a fantastic piece of tone-deaf irony from the creators.

Cool idea. Just a heads-up that the Demo link at the bottom of the page leads to a 403.

> As long as you have Pricing on your website your product is not open source in the true spirit of open sourceness.

It's an MIT license. That IS open source.

If they have a commercial strategy - that's a GoodThing. It means they have a viable strategy for staying in business, and keeping the project maintained.

MIT == OpenSource. Pricing == Sustainable. That's a horse worth backing IMO.

It's not really confusing at all.

Content under backend/ee requires a license, everything else is MIT Expat. Pretty standard stuff.

> Can you call it open source if you need a subscription license to run / edit the code?

MIT is open source, their other stuff isn't. Pretty clear.

Thanks!

I've finished up there now, so this is purely retrospective.

For them - the workaround (sadly) was -- a lack of testing.

I was really surprised that in a heavily regulated environment (this project faced off to a regulator) Integration testing (which has gotten really easy on the JVM thanks to stuff like TestContainers) just didn't exist.

That could be symptom of a broader lack of a test-driven culture though.

The block was not for docker license cost reasons - it was part compliance, and part an issue with the underlying VDI VM they were using.

The onshore team were able to use Docker, but not offshore.

That's not what happened here. The BBC edited footage to make it appear that Trump said something he didn't in the leadup to the Jan-6 riots.

My personal biases are pretty strongly in favour of the BBC, but what they did here was really bad. It's appropriate that heads roll. I wish more orgs would have the same level of accountability.