I am not a fan of AI agents when used poorly either, but this quote is a bit of a logical trap. No customer or user wakes up and says "I hope I get to talk to a human customer service agent today" either. Having to contact customer service at all is already a friction point. If AI or a human or a monkey pulling levers can fix my problem quickly, I don't really care. It's when my qualm is unable to be solved quickly that I will start finding flaws in the process - and because humans lack empathy for machines, it's easy to blame the machine rather than the process.
AI being used to advertise a brand is a different story - absolutely it comes across as insincere and lazy.
That must have been expensive! Thanks for running the benchmark and sharing.
I tested Coducky (my AI review macos app) on the full 50-PR Martian benchmark using qwen3.7-plus via OpenRouter as the reviewer with a lightweight pre-save precision gate with deepseek-v4-flash. The score (gpt 5.2 judge) was 43.0% precision / 35.8% recall / 39.0 F1. That puts it about inline with CodeRabbit. This cost around $7 to run the full 50 PRs.
Your post inspired me to set up a test harness for my app to continue to test model combinations. Coducky allows you to select whichever models/subscriptions you like to run reviews, but it could make sense to build a collection of model combinations that work well for this.
I'm self hosting umami for https://loose-tongues.com/. It's simple, fast, and I have full control over it. It's using postgres so I can do whatever I want with the data. https://umami.is/
AI models on their own are raw, undirected, and inherently probabilistic. A "harness" acts as a control layer wrapped around the model, designed to steer it toward deterministic outcomes. It achieves this by equipping the model with actionable tools like web search or file I/O, and by orchestrating an evaluation loop that runs until an acceptable result is produced. (various analogies work here - an astronaut and a space suit, a rocket and the launch pad/mission control, okay I'm out of analogies that aren't car engines)
You can see this in practice by looking at the leaked Claude Code source code. It is a harness around Anthropic's model built for writing code. It relies on heavily engineered (and sometimes brittle) steering mechanisms. These range from highly specific situational prompts to deterministic, hard-coded logic that executes based on the model's output.
Getting a harness right is incredibly hard and feels like whack-a-mole at times.
I can totally agree on the harness part. When I first set out to create a Cursor killer nearly 3 years ago, I built LLM tools, but when I didn't know then has I tried to wrap the LLM's brain around the tools when it needed to be the other way around.
Looks me off an on three years to realize I was doing it backwards. Agent was originally born after I re-wrote CloneTool, a more generic Disk Cloning too with an SMAppService Launch Daemon.
After I completed CloneTool, I was like mmmmm what is I connected an LLM to the Daemon? It rattled of 50 things it could do and it had no knowledge of this anywhere in the harness, system prompt or tools. It simply had figured out its environment on its own.
I never ran Agent under that scenario it definitely has a hardness now. And yes getting the hardness right is a number one challenge and once you do get it working good with most LLMs out of the box, you try not to change it because that sweet spot is hard to come by. Not to say it never gets tweaked but the further in you go, the more you chringe on a change that may break it.
I actually downloaded this and tried it. Am I the first one here to do that?
As someone who hasn't touched DaVinci products before (but a lot of experience with LR) - I am immediately confused by the integration of photo editing here. It feels very much like video editing software with photo editing tacked on. I can imagine that this would be much more intuitive for people who are already used to using DaVinci for video editing.
I can intuit from the interface that there are a lot of powerful editing opportunities here, but I feel lost in the software. I spent 15 minutes or so trying to figure out how to do simple masking, but I could not find any way to do it for photos.
Obviously this is just a beta and hopefully the workflow will be improved, but unless the photo editing features are extracted in to their own software package, I don't think it's enough yet to sway me from LR (and I want so desperately to be swayed)
If you know how to do masking with video in Davinci, then it all just applies to photos too. I tried today some basic Magic Mask and color tab editing with photos, and it works exactly the same (without the annoying waiting time on huge videos for Magic Mask, ofc).
I've just now had a look at a couple of YouTube tutorials on Magic Mask for video and I think I understand where I got lost. It looks like the tools I was looking for are on the Color tab, and I first need to drag my images in to the timeline at the bottom of the screen and then jump to the Color tab to work with them.
All the tools are here for a good photo editing product - they just need to be extracted and arranged in a way that is intuitive for photo editing, and this would be a legitimate LR alternative.
edit: This is a great video on the Photo tools: https://www.youtube.com/watch?v=HuKgfytA0lg. I do feel a little more confident that I could use Resolve for editing after watching this.
Yeah, it's questionable that Davinci layout will yield a good photo experience, but it's interesting development anyway. BTW, that's the reason I like Photomator - it has absolute minimum of what I typically would use, and it's all there. Like, there is a hotkey for autoaligning horizont (and quite often it actually work), or intuitive AI-powered 'Select subject'/'Select background', and even an easy way to back those typical change into edit that can be applied with a hotkey onto a bunch of photos. It's easy to spot when software was written based on pain points of real end users.
Is it only in the Studio version? Or the 21 Beta release? I downloaded the free version of Resolve 20 and I don't see any evidence that I can edit my raw nikon photos. The "Color" tab looks like it could be helpful if I knew how to turn my images in the media pool into "stills"
Yes, but I think it's important to make that clear. It doesn't appear to attempt to target photographers who are not coming from a video editing background, and photographers will probably be disappointed.
I do hope they split this out to a separate focused product, as the photo editing space is in dire need of more options.
The webpage seems to advertise itself as a Lightroom replacement sort of software?
Which if it is, it better be damn good at it. Adobe may generally suck and Lightroom has many rough edges, but it has streamlined its workflow very well.
This is why I (photographer) haven't switched from Lightroom to an alternative. It's because all the alternatives are targetting different workflows or have a pretty half-assed RAW workflow. We don't need a photo workflow tacked on to something else, we need a proper good workflow made from scratch.
It is unclear. Their marketing material at least does imply that they are targeting photographers:
> Whether you’re a professional colorist looking to apply your skills to fashion shoots and weddings, or a photographer who wants to work beyond the limits of traditional photo applications, the Photo page unlocks the tools you need
Indeed, the hardest part is inoculating without introducing contaminants that will out-compete the mycelium (typically trich).
However, this is relatively simple and cheap to do at home — especially using a technique called uncle Ben’s tek. As it happens, pre-packaged rice is the perfect sterile environment for mycelium growth.
Once successfully inoculated, it’s basically a matter of mixing the mycelium with substrate (wood chips or coir depending on the strain) in a container with a lid that allows minimal airflow (a plastic tub for example) and waiting.
The process is really quite simple, and I’ve harvested kilograms of mushrooms with an initial outlay of around $30. Once you have mushrooms, you have spores, and the recurring cost is only substrate (and uncle Ben’s bags or grains, jars, pressure cooker if you want to sterilise them yourself).
Tofu and wheat gluten have been used for centuries as meat analogues in many cultures (especially those that mostly eat vegetarian). It’s not a silly concept at all, and opens up a world of delicious culinary options to those of us who don’t eat animal flesh.
I don’t think parent was ever saying that tofu was (nor should) be similar to meat in taste nor texture. That is not the point.
You can still prepare and spice tofu just like you would do with meat, and get a complete meal that replaces meat with something else that adds to the quality of the meal just like meat would, regardless of whether the substitute replicates the texture or taste at all.
That is much closer to my standpoint then. I think it’s silly to imitate meat, when there are plenty of delicious vegetarian dishes. For example tofu dishes.
How is that different from saying: "It's silly to eat Indian food [prepared by Americans] when there are plenty delicious American dishes"? No one is forced to eat fake meat, but as vegetarian who likes burgers, how am I silly for eating fake meat burgers? I also eat tofu, vegetables, Indian, Italian, and Vietnamese food, and I think variety is a nice thing to have. Silly me.
I honestly think that meat eaters are missing out when they eat these fake meat burgers (or beef burgers for that matter). You can put so many things between these buns some of these are really delicious. The variety of the veggie patties is amazing. When I order a veggie burger at a new restaurant, experiencing a new kind of patty is part of what makes burgers such a great food.
Yes, I bet meat eaters say the same about beef burgers, there is difference in texture and flavor of each patty. Difference in quality of the meat, the coarseness of the ground, etc. But knowing that, makes me thing that meat eaters don’t actually like the meat part in their diet, and trying to replicate the meat part of a beef burger when making veggie patties just seems like a lack of imagination and an unnecessary limitation.
> I honestly think that meat eaters are missing out when they eat these fake meat burgers
Have you considered the possibility that it is you who are missing out on experiences by refusing to eat these vegetarian alternatives that taste like meat?
"Oh, but real vegetarian food is so much better bla bla bla"
Ignoring your knee-jerk reaction, have you actually tried the Impossible Burger or the Beyond Meat burger?
But nobody claims the experience the of eating ultra processed fake meat is BETTER than the real thing, do they? So how could us haters be “missing out”?
Because it has the taste and texture of meat, which you don't eat. So eating these would be a way for you to experience this taste and this texture, and that should at least have some novelty value for you.
Backing up to the meta discussion, I love how these meat alternatives, and near-future things like cultured meat or synthetic milk test everyone's convictions and prejudices. Why do we eat the things we eat? Habit? Ethics? Preference? Virtue signaling? It's a good way to examine your principles.
You seem to have landed in that these meat alternatives are bad because they're "processed", and everything "processed" is bad. Alright. But would you eat clean cultured meat? Muscle tissue that has never been inside a living animal, and yet is indistinguishable from meat that's been cut out of a slaughtered animal?
And going further out, would you eat cultured human meat?
Since I eat normal meat, I’m not missing out by not eating fake meat.
I’m generally against fake and highly processed things, I don’t want them in my life, and definitely not on my plate. That would definitely include lab meat. So I’ll keep eating regular meat until the fake meat industrial complex gets it outlawed, and then I can just eat vegetarian food.
During my life as a vegetarian/vegan I regularly consume “fake meat” products because they are simple to prepare and allow me to use recipes that are not vegetarian. For example, it’s extremely hard to find a good vegetarian burger — the beyond burger was a revelation the first time I tried it. I still like burgers, even though there are many wonderful vegetarian dishes. I didn’t stop eating meat because I don’t like the taste of meat.
Imagine that many of your favourite dishes, those you grew up with, were suddenly unavailable to you because some ingredient no longer existed. If a new ingredient hit the market that was not quite the same but was a convincing substitute in taste and texture, would you consider it silly and avoid it?
Maybe in that dystopian future where bacon doesn’t exist and I get very nostalgic for the carbonara of my childhood, sure.
But that’s not quite what we’re discussing. Meat exists but some people want to go vegetarian without sacrificing anything. I suppose it’s pretty similar to the logic of people who want to lose weight without giving up sweets or soda, so they switch to aspartame versions.
> Meat exists but some people want to go vegetarian without sacrificing anything.
Yes, how dare they?!? How can you call yourself a vegetarian without sacrificing anything? If anyone could be a vegetarian, there wouldn't be any moral superiority for the real vegetarians! Oh the horror!
I’m not vegetarian and it’s not about feeling superior.
I just happen to think fake meat and fake sweeteners are some of the most absurd things in modern society. I prefer food to be natural and unprocessed.
It’s very common to use it on the HTML element, less common to use it on elements further down the tree. Like many accessibility features of the web, it’s often neglected by developers.
AI being used to advertise a brand is a different story - absolutely it comes across as insincere and lazy.