I have found that I need more than this. A document viewer is critical so I can see HTML prototypes, review docs and other output and give feedback contextually inline (through a commenting system). I also need a task lists for my project/ agents so I can see where things are. I created an app like this for myself that is built around an integrated terminal, after I had the epiphany that VS Code (and VIM) were becoming the wrong tool because I am not actually spending time _writing_ the code.
fine, I need an "integrated agent collaboration environment" instead of an integrated development environment. I find value in them all being in the same app because it brings everything I need into a single work flow.
Kind of. I tried it on a really small project, but I've been reading about it and have seen a few demos and reviews. It is still too 'code focused' for me.
For context, I am a product manager at a big tech company who has been building side apps for fun (and profit) since the days of Palm OS. I am effectively an SDE1 with 20 years experience, who has deep expertise in a lot of obsolete tech (C, Objective-C, Perl) and some exposure to modern stuff (TS, React, Rust, Swift).
In the past year, I've been able to personally drive projects several orders of magnitude than what I could ever build myself. I'm not asking Fable to 1-shot grand theft auto, I am creating steering files, running adversarial reviews, prototyping, automating testing, and building my projects the slow way. Still, I don't write any code, just requirements and prompts and generate the rest. Our internal development teams at my company have arrived at a very similar process (much more sophisticated) by investing heavily in steering files that encode development approaches, harness and other mechanisms to automate best practices. It is getting to the point where our development process are becoming really similar, and many of the SDE do not need to review code for the majority of their deliverables, instead they are working on the framework (harnesses) and auditing. (Of course they still do look at the code because the love coding. But they usually don't need to)
I keep telling people that we are living in the golden age of AI - like the first year or two of google. It is all down hill as these companies push for profit and lock-in.
There are no open source models. Only open weights. No one is giving you the source (training data). And yeah, no one is giving you the compute to train the models.
Yes, there are. But that's not what I was saying. I'm talking about harnesses, tooling, sharing training data, the shared research, and the list goes on. Frontier labs are already trying to move everyone into the cloud so their harnesses and surrounding tooling can be hidden away. We need to make sure there are strong open-source competitors to this model that keep the power on the local machine.
Does Nvidia's acquisition put the open-source ecosystem at risk? I remember what Oracle purchased Java. IMO, it was a mess for many years after that. It is a strategic move for Nvidia, but I see it harming open-source AI options.
1. Download ollama and give it a try. It doesn't have to be that one but it's an easy on-ramp. Just get a feel for what open source/open weights is capable of
2. Mention it whenever it comes up. Most people have no clue this is a thing and I think it's useful to make people aware. We need access to uncensored / unbiased LLM models - information wants to be free but there are plenty of businesses gunning for regulatory capture as these are very powerful tools.
3. If you're in a position of developing any project that makes use of AI in any form, check the open source models first, unless you absolutely require the best of the best, these other models are pretty dang capable of almost everything any commercial model can do.
4. If your state or {insert legal jurisdiction here} attempts to regulate access to open source tools for this, oppose it with your vote and your voice.
5. Opposed laws that grant commercial AI suppliers any priority or premium access under government purchasing programs.
I'm sure others will chime in, those are a few that pop the mind.
Weren't people pissed off at them for a variety of reasons? Not giving attribution etc.
In case anyone wants other good alternatives, there's llama.cpp and vLLM, each harder to setup but opens the door for squeezing more performance out of your hardware.
You could also vote with your valley and support orgs that release open weights of their near-SOTA models, though nowadays that means giving cash to primarily Chinese companies (e.g. Moonshot and Z.ai). For what it's worth, people are also complaining about them decreasing usage quotas on their subscription offerings as well so seems like the squeeze is everywhere, even DeepSeek raised their prices (which is better than them going broke, I guess).
One issue is that models are only one part of the equation. Search is also extremely important, and for that you pretty much have to depend on a third-party service.
Unsubscribe from Anthropic because they block third party harness on subscriptions.
As long as you keep providers replaceable things will be fine.
Google, Facebook, Apple etc were much better deals around 2010 before they became entrenched and irreplaceable, and thus able to extract & enshitify without people leaving.
In many countries Meta platforms—Facebook, Instagram, WhatsApps—are primary means of communication. If you want to find interesting events happening this weekend, you need to be on Facebook. In this regard, Google and Apple are much easier to leave because they offer personalised services, and you can always move your email and photos elsewhere. But you cannot move other people from Facebook or Instagram.
It’s not that easy to leave Google or Apple. As an example I wanted to leave iCloud and stop paying storage tax for Apple. But they have made it almost impossible to migrate the photos. There is no API to download the photos programmatically and the only way is to sync all the photos to MacBook and then move it. However, the photos are close to 1TB of storage and my MacBook doesn’t have enough storage to sync all those photos locally.
Same goes for Gmail. I have used my Gmail address for countless services and it’s almost part of my official identity. The benefits of moving away from Gmail doesn’t justify the effort I have to put in
> I have used my Gmail address for countless services and it’s almost part of my official identity.
This has been a topic for over a decade now, I think. People have been recommending getting your own domain. Best time to do that was ten years ago, and the second best is today.
For you, sure. But there are a lot of communities running entirely there. Our local farmer's market is preorder only, and is entirely run off Facebook. I would have to skip going there altogether.
And it's not viable to propose any alternative. There is no platform, closed or open, where there are enough people registered to be actually usable, and nobody will make a separate account for this.
By sending some cash (and maybe some non-sensitive training data too) the way of labs creating open models? At work we have expensive Anthropic and OpenAI subscriptions but also have some in house workflows plugged into DeepSeek and GLM APIs.
A pull request is a communication to the project. AI or no AI, a poorly communicated request is a burden. IMHO AI prs are fine as long as the submitter has done the work to refine that communication to make it easy to read and assess.
A large submission without a breakdown or explanation, or a pass to minimize the code change is junk. The operator can literally ask the ai to compose it better, refactor in to smaller PRs, or do it themself. The annoyance is to have to communicate and enforce expectations to drive by submitters. In the end every project has to figure out what they accept. If, at a glance the PR is drive by junk being thrown over the wall, a response of this doesn't meet our pr submission standards delete, or try again, to me is not overly burdensome.
I for one am running what I can on my aging 1080Ti(!!), namely a Qwen2.5 14B (4-bit quantized). It’s not great, and the only other card I have is a 3070Ti but I need that for gaming. :(
What a terrible card that 3070Ti is. Mad regrets buying it because I wanted to save $400 compared to a 3080Ti.
I really don’t understand why this is being downvoted? Did I say something wrong / controversial? Or is it because I’m not using my resources the “optimal” way? Is it because my models aren’t open weight? I was only trying to contribute my experience :(
I haven't used Kimi K3 or GLM 5.3, but boy am I glad they exist! Every time an open weights model is released a bit closer to the frontier models, that's another level of performance that we, the users, can't lose access to no matter if the frontier labs jack up prices out of our reach, or the US administration decides to put a full export block in place on AI.
Google was pretty amazing for about 15 years, not 1 to 2. Google rocked from its launch (1999ish) until around the time it shut down Google Reader (2013ish).
The actual reason was when they pushed Google+ and tried to make that the centre of Google. Everything else that had a social element had to be killed. Anything that breathed the same oxygen as plus got the boot.
Including the inanity of the + operator being a "this word unchanged must appear in results" modifier. So when they hot patched search, it broke, as +aliens looked for the plus name aliens only.
Then some bonkers spokesperson for google said "oh just use quotes", which at the time did nothing even remotely the same. I loath this person for eternity, her lies, and her waving off of reporters concerns.
Thus verbatim was introduced, validating quotes weren't the same, yet which wouldn't work with date ranges, and is lame.
So goes the "professionalisn" of Google, or "screw around like uncoordinated idiots".
To say Plus was inane and destructive to Google is vastly understating. And everyone involved in Plus were buffoons.
You know, I wish could speak freely on this topic, but as a public forum, I have held back some vitriol.
It's cynical and critical of marketing? Many of us are cynical, and there's an argument that being cynical is lazy because most of its arguments are obvious because they are rooted in truth.
> Yes. Grab those open-weight models while you still can.
You mean like it's impossible to download a movie because it's illegal, it's going to be impossible to download open-weight models because it's going to be made illegal?
So for the same definition of "impossible", it's going to be "impossible" to download open-weight models?
luckily I have purchased a used amd mi50 32gb card for pretty cheap back then. while I haven't used it extensively, it feels pretty great having a backup plan that does not depend on any external 3rd parties.
I just have to add on about how great Fastmail is. They are completely focused on having a stable product, that is relatively simple and cheap. They are not ambitious as a company at all, in the best possible way. They haven't tried to build an office suite. They don't upsell me on any new features. They just deliver a solid, basic product that has been consistently good for more than a decade now. I wish more software and services were like this, I'm tired of everyone hiring an MBA and following the exact same "maximization" business model.
I think you're missing the point. The folks pushing 996 (and willingly working 996) feel like they are in a land rush, and that AI is going to accelerate their ability "take the most amount of land" No one is optimizing for the "9 to 5" oriented engineer.
In what sense? I have a Switch 2 without NSO and it does not allow online play. It also, in the default configuration, needs to authenticate before even entering the online shop. In that scope, it doesn’t even need to have any parental controls.
The reason I don't want AI integrated into my browser (or really anything else) is that the mental model for big tech moved from "providing value" to "capturing value" about 15 years ago, and I expect they will try to use this integration in an attempt to build a layer between the customer and all downstream services (stores, banks, information) so they can extract some form of tax on every transaction (ads, micro-fees), all while consolidating data about me to create new sources of revenue. I am one of those 'bright minds' who has wasted their talent improving marketing conversion by 0.001% instead of working to cure cancer. (Let's be honest, improvements are way better than 0.001%, I am good at my job).
My personal belief is that we can’t control every thought, but we can make sure we’re in a positive feedback loop instead of a negative one. For example, when I am getting negative, I’ve learned to take a step back and try to figure out why. If I can’t get myself in a better mood, I go to bed early and generally wake up happier. I also try to structure my days to make time for the things that make me happier (exercise, eating well, friends, family, hobbies) and cut out things that make me feel more negative (social media, news, sugar, etc). Not perfect, but it helps.
I don’t understand the appeal of smart home devices. My Honeywell thermostat may not be as optimal as the nest but I’ve had it for thirty years and it just works without thought.
I have found the the secret to a Todo list is to create the habit to keep it up to date and actually use it to prioritize your time. The list tool itself is much less important.
exactly. i, too, have tried many of the pieces of software mentioned and my problem is one of executive function, not of tools lacking some quality. currently i'm settled on apple reminders (so i can say "siri, remind me to do x tomorrow at 11am) and then a physical notebook to actually schedule and write checkboxes
reply