MrOrelliOReilly

For me, the killer feature would more be _autocomplete_ for art. I love to cartoon and doodle, but don’t have the time/patience/skillset to build professional digital assets. If I could go from my pencil drawn sketch to a flashy png, that would be awesome! I think it’d be a nice use of AI, since it just allows me to do more with my own creativity.

Unfortunately whenever I’ve tried uploading a sketch to ChatGPT or Gemini, it seems to fixate on details of my sketch, and recreates my mistakes in high fidelity. It fails to take a creative leap toward a good result. I’ve heard some professionals have gotten good results building custom workflows in ComfyUI.

I will ruefully admit that I had also planned a similar blog post! I am hoping I can still add some value to the conversation, but it does seem like _everyone_ is writing about agentic development right now.

This is a great consolidation of various techniques and patterns for agentic coding. It’s valuable just to standardize our vocabulary in this new world of AI led or assisted programming. I’ve seen a lot of developers all converging toward similar patterns. Having clear terms and definitions for various strategies can help a lot in articulating the best way to solve a given problem. Not so different from approaching a problem and saying “hey, I think we’d benefit from TDD here.”

And I just predict how you’ll predict

I believe there are valid critiques to be made of prediction markets, particularly on the morality of allowing bets on events with serious/market outcomes (the market could create an incentive for an insider to actualize that bad outcome, hence we should ban the market as it increases the odds of a bad outcome occurring) or on the negative repercussions of gambling addiction. Instead of making either of these valid arguments, the article instead decides to critique the epistemic value of prediction markets. It comes off to me as ill-informed handwringing and tribal signaling, rather than bothering to engage critically with the topic and offering a meaningful critique.

One means Yes and one means No, this should be clear!!

/s

But they do have utility functions, which one can interpret as nearly equivalent

Appreciate your perspective and totally understand that at some point you just have to ship it! From the outside it looks like a bit less time on XYZ feature and bit more time on marketing polish might have been a good call. But can only speculate what the trade offs were internally. Best of luck maturing the product!

I appreciate the Fly.io team’s enthusiasm and am optimistic this will mature into a product I’d pay for, but my initial impression was of a lack of polish.

Documentation is sparse, or not even available? The API docs don’t tell you much about the service itself, and a Google search for docs returns an inaccessible website as the first result (https://docs.sprites.dev). Blog posts and forum threads and Claude skills shouldn’t be a substitute.

The snappiness of the sprites is very cool and I can definitely see it integrating into future Claude Code workflows. But the lack of a base container images means you’re still doing setup work on the sprite before you can begin development. I understand the philosophy is that sandboxes should be persistent, but Claude Code sessions also work better when isolated from each other, so it’d be nice to have some precepts to get a workspace setup quickly (given agentic coding is clearly a target).

I also found the CLI unintuitive but maybe that was just me!

So very cool idea but left with the impression that the Fly.io team’s should have spent a couple weeks on polish before shipping.

For everyone defending these actions on the basis of Maduro's own corruption and the desires of Venezuelans, I would encourage you to research the history of American intervention and regime change in Latin America. It is impossible to anticipate the second and third order effects of this change, and how it will be absorbed in the local politics. We are witnessing the return of American military intervention in Latin American, nothing more and nothing less.

To everyone proclaiming that we should turn to Venezuelans to assess these actions, how dare you assert that Americans have no autonomy in the actions of their own government. It is tremendously unfortunate that congress has forfeited all decision making authority to the executive branch, but as our democracy was intended this would amount to an act of war, which would require authorization by congress.

The author makes effectively the same comment that twenty minutes late is normal for Germany (below). I don’t have any statistics, but anecdotally I’ve had worse experiences with DB than in the UK. DB does not just run late, but has a bad habit of teleporting you to random German towns, from which you must quickly route find to your original destination (as is the exact story of the post).

> It is twenty minutes late. I consider this early.

There has been a lot of discussion on this recently in the blog-o-sphere. All conclusions I've seen so far are that the economy is basically fine and maybe people's expectations have risen (I'm oversimplifying). I'm also quite eager to hear different conclusions, because there is a lot of cognitive dissonance on the economy right now.

- https://www.slowboring.com/p/you-can-afford-a-tradlife

- https://www.slowboring.com/p/affordability-is-just-high-nomi...

- https://thezvi.substack.com/p/the-revolution-of-rising-expec...

- https://open.substack.com/pub/astralcodexten/p/vibecession-m...

Try a commuter train in Switzerland. I work two hours on the train every single day with no issue!

Totally, however OP's point was that Claude had to compensate for deficiencies versus a state of the art model like ChatGPT 5.2. I don't think that's correct. Whether or not Opus 4.5 is actually #1 on these benchmarks, it is clearly very competitive with the other top-tier models. I didn't take "state of the art" to here narrowly mean #1 on a given benchmark, but rather to mean near or at the frontier of current capabilities.

Yes, I personally feel that the "official" benchmarks are increasingly diverging from the everyday reality of using these models. My theory is that we are reaching a point where all the models are intelligent enough for day-to-day queries, so points like style/personality and proper use of web queries and other capabilities are better differentiators than intelligence alone.

I think this is a total misunderstanding of Anthropic’s place in the AI race. Opus 4.5 is absolutely a state of the art model. I won’t knock anyone for preferring Codex, but I think you’re ignoring official and unofficial benchmarks.

See: https://artificialanalysis.ai

I agree that it's annoying to have competing standards, but when dealing with a lot of unknowns it's better to allow divergence and exploration. It's a worse use of time to quibble over the best way to do things when we have no meaningful data yet to justify any decision. Companies need freedom to experiment on the best approach for all these new AI use cases. We'll then learn what is great/terrible in each approach. Over time, we should expect and encourage consolidation around a single set of standards.

I have been fighting the same bizarre quota demon. Scripts kept timing out due to quota limitations, but I haven't been able to find any indication of a limit in the console. Finally gave up and switched to Claude, since they at least have a sane interface for API keys and billing!

I find this a bit disingenuous.

If I visit a buffet looking for a healthy snack, but 90% of the dishes are fast food, then I'll probably spend a lot of time looking through the fast food, and may even eat some as the best worst option.

Similarly, I have found the overall content pool to have significantly worsened since Musk's takeover. The algorithm keeps serving me trash. It doesn't mean I want trash.

As someone who has recently been fighting bugs from representing very simple math with floats... thank you!

This is incredibly useful! I was manually generating my own model comparisons last night, so great to see this :)

I will note that, personally, while adherence is a useful measure, it does miss some of the qualitative differences between models. For your "spheron" test for example, you note that "4o absolutely dominated this test," but the image exhibits all the hallmarks of a ChatGPT-generated image that I personally dislike (yellow, with veiny, almost impasto brush strokes). I have stopped using ChatGPT for image generation altogether because I find the style so awful. I wonder what objective measures one could track for "style"?

It reminders be a bit of ChatGPT vs Claude for software development... Regardless of how each scores on benchmarks, Claude has been a clear winner in terms of actual results.

Did you actually see the bird? Some animals make sounds that are deceptively similar to birds (ex chipmunk chirps). Merlin won’t recognize these as “not a bird”; it just doesn’t recognize the sound at all.

Usual disclaimer IANABL (I am not a bird lawyer)

Completely agree. This should be well beyond accusations of corporate bullying. It's one thing to mention Legos, it's another to actively include a brand name in your product! NikeGPT, CocaColaGPT and IkeaGPT will face the same issue ;)

Yes, agreed. For me, quitting social media went hand in hand with a recognition that I maintained superficial contact with a large number of old friends. My relationship with these people was already “illusory”, or at least unsatisfying. Now my relationships are the product of active work, which I find more valuable, even if it means maintaining contact with a smaller group of close contacts (outside my day to day relationships). It doesn’t mean my relationship with old friends and family has died… we just have a lot more to catch-up about when we talk to each other!

As a someone born and raised in the Northeast now living in Switzerland I can confirm that the cleanliness, orderliness and array of machinery is indeed typical in Switzerland :D But don’t let this bridge promo fool you, you’re just as likely to deal with roads closed to construction as anywhere else… the cost of well functioning infrastructure is that they always seem to be working on it!

Great addition! Like others, I find it helpful to review how smart people are using Obsidian and related tools to create a second brain. I know it’s popular to critique these posts as onanism when we should just “get things done”, but Obsidian really has allowed me to accomplish all sorts of productivity flows that I’d have needed custom software for previously. It’s OK to wax about your favorite tools when you’re actually using them :)

One thing I’d note is that language models like Chat GPT really do seem to me to be the next frontier in productivity apps. The author mentions using it to simplify search, but you could also imagine a model that recommends related notes in your Zettelkasten or automatically creates links to relevant Wikipedia pages, etc. It’s an exciting area and I hope the author shares what they uncover next year!!

I believe the parent commenter is referring to Julia Child :) https://en.m.wikipedia.org/wiki/Julia_Child

So funny I missed this behavior. Maybe the feedback then is there could be more gradations/tweaking for us slowpokes out there (especially since it appears other folks missed it as well)

Also I should have lead my original comment with kudos to the maker, didn’t mean to only leave (apparently inaccurate) critical feedback!

It'd be more fun if you somehow got "bonus points" for reducing the time between clicks. I kept playing it safe trying to time the ball but it kind of felt like cheating!

Wow. The parent comment did not state they then sifted around for personal data. They checked if there was a bug and found it. For all we know the personal data is front and center, so this rudimentary check also revealed personal information. It’s not like they said they downloaded the SSNs. Good job a miming the ignorance and bad faith of the nameless bureaucrat the parent comment mentioned though, maybe this is just satire and I’m missing it..