JofArnold

Both the worst and best cases seem to require us to do nothing.

I've found it outstanding at isolated long running tasks (eg completed one of our tests in 3 hours and a 100% accuracy score versus 5.5 xhigh's 10 hours and 90% accuracy). For short tasks it seems very Claude'y (hard to express exactly what I mean by that) which I'm not a fan of meaning I'll stick with Codex for that use case and maybe Fable for those times I can for sure benefit from it.

Let's say you could follow and unfollow once a second and they knew it. Then you could replicate the dots and dashes by the length of time you toggled the status plus the gaps where you weren't toggling at all.

Eg in the first ten seconds 10 toggles, in the next 10 seconds a 5 second gap then 5 toggles. That would be dash, quiet, dot.

Run prettier etc in a hook.

It's worth checking who the author is... Cristian's not exactly new to the game. I think he's being humble he doesn't know something despite his experience.

Thank you, that's very helpful. I think I could get close to that in some coding sessions where I'm running multiple in parallel but I suspect it's very very rare. Even with token efficient gpt5-codex my OpenAI bill is quite high so I think I will switch to Pro now.

I'm thinking about switching to ChatGPT Pro also. Any idea what maxes it out before I need to pay via the API instead? For context I'm using about 1b tokens a month so likely similar to you by the sounds of things.

Same. 30m tokens in a few hours (of which many were cached it seems and only a few output tokens). I use Gemini to solve only specific problems and in my case $20+ was worth it.

That's brilliant and even more absurd than mine!

One of my favourite exchanges with Gemini saw it arguing with me that what I was asking of it was wrong. It culminated with it declaring (approximately) "I cannot in good faith continue to design for you something that is objectively flawed" and then refused to go further. Of course, Gemini was wrong and when I proved it without doubt it replied in a style that suggested it "felt" shame. Quite odd and very funny.

Neo4j?

Recommendation: add more info to the home page to describe what it does without requiring sound. To evaluate this in a work environment I'd have to use my headphones which is an extra step I might not take unless the valid add and the product itself are very clear.

One of my first jobs (~1999) was as a research assistant working on seeing whether it's possible to make reentry vehicle heat shields from oak. Sadly, it wasn't.

I used magic patterns for a couple of months and it was one of the first no brainer AI services I've paid for outside of the main LLMs and IDEs. It did such an amazing job on quite an esoteric frontend that's very much not your normal web app. Impressive. Next time I need to design and build some more frontend code I'll be subscribing again.

Edit: to add some meat to that comment what surprised me was just how much better it was than Anthropic and OpenAI tools at that time for coming up with great looking products with minimal prompting. I also fed it other designs for inspiration and it replicated them brilliantly while incorporating my requirements. Good stuff.

Congrats on the launch. Another happy user here. (Caught a really sneaky issue too!)

I've found an air fryer on dehydrate works well. The Ninja I use controls temp within a few degrees and will happily do so for hours at up to 80C (actual recorded 80C unlike my filament dryer). Also relatively cheap and compact. Worth looking into. Only downside is there's not much space inside the drawer and you have to keep turning it to get an even drying as the air circulation is restricted.

This is great (in theory). During lockdown I got an ambisonic mic (Rode NF-SFW1) and used it to create Dolby Atmos experiences. The workflow - including sending it to Dolby's tool every time - was such a pain. Adding additional 3d elements was especially annoying and limiting.

Unfortunately that's no longer my hobby so can't test this for you but definitely scratches an itch for past me. Nice

R1 is the first model I've used that one-shotted a full JavaScript tetris with all the edge-case keyboard handling and scoring. It also one-shotted an AI snake game. With the right prompts I've found it consistently better than o1 and Claude 3.5 Sonnet.

The other thing is you'll need markers. At least in my experience. I think if you don't need precision photogrammetry and AI will get you the results way faster

(To be clear I love my Vega. Game changer. Just a bit heavy handed if you're not making car body parts)

This is the kind of comment that can change a person's life. Really thoughtful. I'm going to quote it in future. Thanks.

Good timing given computer use was just the other day jailbroken and "succeeded" in ordering an assassination via the dark web.

I definitely recognize what you're saying and it's fantastic, but hiring managers and execs do indeed need to be active on this too.

The channels to reach out to more diverse candidate are more often than not different to those recruiters use to find your "average white guy in a hoodie". That's decreasingly the case for women (and I use that term very intentionally; I'm not talking generally "non-male" here), but social media and professional networking is quite hostile and/or intimidating to other groups. While the business benefits of putting in this extra effort in are obvious (it's a no brainer to seek out overlooked top talent, let alone the benefits of culture and diverse experiences), those benefits aren't always aligned with the hiring team who are incentivized in most companies to hit numbers. The business goals need to be driven from above by DEI initiatives or - if not - hiring manager allies who'll put their foot down.

I suspect you're right. But I've just last night finished Brave New World and what strikes me is production of children in that book almost entirely for the purpose of labour.

So, I'm curious what the driver for reproduction will be in the future once robots are capable of doing all the work and humans live for a very long time. I don't have children nor intend to - so likely this is a very cold take that doesn't apply to most - but the cynic in me says we've so far focussed on reproduction as individuals and at a country level to maintain productivity and extend the health and wealth of their elders. Without that pressure, would people choose to have fewer children on a scale we've never seen before?

I wonder how the probability of securing such a job - with huge layoffs lately and increased competition - compares to the probability of business success. There's unemployed engineers grinding at system design and algorithms 10 hours a day for at least half a year to get an interview. If I'm going to spend hundreds of person hours on something, I think I'd rather start a company to be honest. Additionally, internationally those levels of pay are incredibly rare.

This is the approach I use to get ChatGPT to generate images that get around copyright. E.g.

Me: Create something in the style of Escher AI: Can't due to copyright Me: Precisely describe in detail <insert artwork here> such that I can use it as a prompt to generate an image AI: <prompt> Me: <prompt>

9 times out of 10 it works really well.

I love this and applaud it.

It's also very timely: next week I have arriving a portable 3D scanner (an Einstar Vega) precisely because as a hobbyist sculptor the only way I can analyze these works to inform my practice is to go to galleries and scan the works myself (sometimes very surreptitiously!). It's crazy that I need to buy a £2000 piece of equipment and produce have a tonne of CO2 just to be able to look at a piece of art from x00 years ago on my computer.

Bravo.

Here's a fun one I just made for you. Slightly inspired by OP https://claude.site/artifacts/698c26f4-2f60-428b-8ae0-ac7a29... Took about 15mins of prompting and iteration. Need to press start audio and then drag your mouse around.

The prompting is more interesting than the end result though, in my opinion.

Sorry. You're right of course. Won't do it again.

Really cool. Related, I asked Claude something like "create a multimedia interactive web experience with audio and mouse interactions" a few months back and it produced something fairly similar. My favourite follow-up prompt was "Make it more Stranger Things" and it turned the background music - which it generated - into a pulsing synthwave sound.

I really need to post these art experiments as some are truly mind-blowing for a machine that can't see.

> usually involves deleting entire designs

Yes, for me that's usually around the point I've got a huge and complex assembly with all the motion wired up. Right-click -> Duplicate -> Rename "MyProject V2".

I would save a huge amount of time also this way.