You can try open models via OpenRouter and omp without having to buy or rent any GPU. I routinely try open models to see where they are. GLM 5.3 with DSFV4.1 as advisor via omp feels Opus 4.6 level, i.e. totally able to ship stuff.
I do use Anthropic and OpenAI mostly because it costs me 1/40 and 1/50 of the api prices, which is way cheaper than Chinese subscriptions, but I’m ready to jump ship when they pull the plug. Fortunately they have nothing that forces me to keep paying them, and I don’t pay the crazy enterprise subscription costs, just the personal account prices.
I also die to be able to run the OSS setup locally to stop being spied on all the time.
For context, I averaged 10 hours a day prompting LLMs from when ChatGPT came out. At the start it was just function generation, then single file modules, then modules, and now I reason, design, implement and test with them.
An interesting thing is that with omp you can plan with a smart model and then implement with a dumber one. So for example, plan with Kimi 3.1 via OpenRouter and then implement with DSFV4 with zero data retention active, sorted by cheapest, and minimal tps accepted.
I get the people who are pissed about their cushy jobs evaporating, but if you know how to use these technologies it’s very freeing because it’s like having a company of people working for you, except they are not human so they’re not wasting their life working for you instead of using it for themselves.
You can make them do pretty much everything that is fuzzy-verifiable, you don’t have to worry about their feelings or that they won’t do what you asked them to do or stop, and you can activate them when you want at scale in parallel or not use them at all for days.
For me it’s a dream honestly. I never felt so much empowered in my life while being enabled to unlock my creativity with almost no boundaries.
As the OP said really. It is very very freeing to just be able to give a task that in ye olden days you knew was going to be a pain in the arse to do, and it will do it without you. Amazing.
It's like having extra copies of yourself that you can just fork and get stuff done. E.g. the other day I was in a meeting and there were some heavy discussions about a few gnarly issues. I fired off a few prompts in parallel while the AI researches options, approaches, made a prototype etc all while I was present and paying attention still in the face to face meeting. I am so much so much more efficient as an engineer now - getting better feedback, more bonuses etc. It's never been better - I handle thinking about the requirements, the computer science and software engineering big picture etc, and the AI handles the syntax trivia for implementation.
The models are really really good now.
The only downside is that as a result of more stuff getting done, we need to have more meetings to discuss what actually needs to be worked on.
You didn't really answer the question though, how are you not nervous about your job security and how do you still see any value in software that you make with almost 0 effort?
People at work are cutting and pasting Claude output for use in routine messages on Teams, troubleshooting suggestions, and proposed architecture designs, and honestly it's some of the dumbest shit I've ever seen. I have to tell people to reword it in their own words, and I believe they often can't.
I've seen developers use Claude to make suggestions for infrastructure design that made absolutely no sense and did not consider our environment. I've seen people write English that grammatically made sense but logically did not.
I don't see enough complaints about this and it can't be just my company.
Is anyone else seeing really severe Dunning-Kruger?
I always check what AI says to me, and I use my own words. I think the average engineer is not.
That it's a degradation in some environments? There's not a lot being said about this. The laments are usually developers sad that they're prompting instead of coding. My lament isn't about the art of it, it's the human reasoning that seems to have gone away in my workplace when it comes to engineers.
Think bigger. Don't think in features. Think in business workflows.
You are a consumer, so you naturally think like the consumer you are. But consumers want cheap stuff and only big big businesses are able to provide cheap stuff at massive scale. So stop thinking in b2c. For us little businesses the money is in b2b. Businesses pay lots of money to have problems solved. They want to focus on their core business and outsource the rest.
Consumers hate paying subscriptions. Businesses love paying subscriptions. Because then they can make their problems someone else's problem and focus on what their actual business is.
Maybe it’s 1% or 10% today, but a decade ago, having/assembling the technical chops to know how to build something was a huge part of the meat / barrier to entry.
It can still be true though, because entry is nothing without sales and a continued search for product market fit. I don’t know about 1% but if you say ‘for every 100 apps launched in 2015-2020 only 1 turned into a sustainable business’ I’d say that’s in the ballpark.
If code becomes cheaper that may change the business fundamentals but it also means capturing customers becomes way harder.
Even a decade ago marketing/growth was the massive lion's share. IMO just building something has been near meaningless since at least post-Ruby on Rails. The app stores have been inundated since the late 2010s.
In a former life I was a freelancer who built first version mobile apps for seed and pre-seed startups. I’m a decent dev, so what I built was always good enough. Virtually none of these startups survived, and there were dozens of them.
I've hit a weird point myself. I'm not overly interested in building software for other people now. What I'm able to do is build all my stupid hobby project ideas for my very specific use cases and not have to worry about making them profitable in order to justify the time spent on them. I just built my own point of sale system because nothing on the market meets my needs, and my needs are extremely niche.
I sell vintage cameras in an antiques centre, but only 3 days a week. I’d like to sell online too but I have no ability to put aside stock for that, and similarly I only have access to the stock a few days a week, which makes shipping awkward. Pretty much every item is unique and needs listing separately, which is a pain. This is probably doable on some existing POS but it’s almost certainly much more expensive than just building my own (I think Shopify starts around £40 per month for what I’d need, then still require a lot of customisation). A major aspect of my business is buying stuff in the stall and tracking its eventual sale price, which tends to be a pain on other systems when it’s all one-off unique items.
I also do repairs and so I recently added a job management system into the POS, which has been really useful so far. Next step is to sort out the online store/eBay integration aspect!
Take your time to set up the tools and just build something small. Create a personal website, or a calendar that helps to track friends' birthdays, or something else of that sort. It's a good way to calm yourself down, because it will give you a good picture of both the capabilities and the limitations of AI.
I've found it very liberating that I can handle some of the tedious parts of a project to AI. In the end, I spend perhaps the same amount of time on a project, but more of it goes to important work and less gets wasted on plumbing.
People are underestimating the lock-in of Claude Code and Codex. Most companies are not buying a model, they are buying the ecosystem.
But the lock-in is not _that_ big that a big co could not pull off a migration, but it would be like migrating from Teams to Slack, not like migrating away from Adobe.
This is exactly how I got people at work onboarded to our local models. Everyone was comfortable with Claude or codex CLI so i gave them prebaked config files to use them with our local models. Ezpz
They do when they see the cost savings and ROI. It’s the one reliable thing that makes a company switch from any tech to another one.
Looking at our AI spend today vs 1 year ago we have massive changes. Anything that can bring this under control and potentially save millions a year is being explored.
We will probably end up with a combo of open weight models for most work and frontier models for key projects. For now. Who knows what the landscape looks like in 1 year.
In OMP just setting the "task" role (which controls the default subagent model choice) to some cheap Flash model like Deepseek or Gemini goes a long way towards making better use of your quota.
Sol and Opus both are quite eager to use subagents and since the subagent tasks are often well specified and then verified by the main model there's hardly any advantage to using anything better for the subagent anyway, so IMO it's a no-brainer.
For me switching the main model to Kimi K3.1 Pro would put me towards 100% open, but I don't know if it uses subagents effectively. Any other open models I noticed just don't utilize them very much.
I mean, they kinda tried to regulatory-capture the market after trying to scare the public, possibly because those models will be a cheap option that gets the job done?
For now, I think everyone is still using Anthropic and OpenAI because if you use a subscription you pay 1/40–1/50 of the API prices, and the models are good when they don’t nerf them, and they are also way cheaper than open models’ API prices.
The interesting thing will happen when they pull the plug and become economically smarter to stop using them. I regularly try alternatives to avoid being locked in and found GLM-5.3 as an orchestrator and GLM5.3 Flash + OMP and DeepSeek Flash as advisor to be able to get jobs done just fine. Space Bunny too was pretty great, which was probably MiniMax’s new model.
I think they are using an Uber like strategy but without the network effects that justify losing money for so long
I do wonder why, like clockwork, there’s an article against prediction markets. I do wonder if the problem with them is that it creates an incentive to share the truth, or for very smart people to predict it, and for others to use the predictions as a valuable reference point. It would be interesting to track what is shared and how often to see if there are some patterns
> I do wonder if the problem with them is that it creates an incentive to share the truth, or for very smart people to predict it....
You missed the obvious one: it creates a path for people with insider knowledge to monetize it at the expense of employers, institutions, etc.
The guy using his access to classified information to make a few hundred thousand bucks in a day is not interested in "sharing the truth" for the benefit of society.
Right, and I'd also like to preempt any apologetics trying to cloak it as socially-beneficial "information discovery."
Many of these betting/insider-trading scenarios are structured so that the information only becomes revealed at the same moment it becomes worthless. (In some cases, that's just a return to its default state.) Like the value of knowing the winning numbers from an expired lotto draw.
When I saw Ratsphere types pushing these kinds of markets years ago getting insider information was the primary selling point.
It’s not inherently stupid - I’d much rather that some lowly analyst sell out an impending stock hit for a few grand than well-positioned insiders soak the market for 10,000x that. There’s obvious moral hazards, though.
I switched to oh-my-py and never looked back. I guess having an incentive to maximize (expensive) token usage, and LLMs degrading with higher context, isn't aligned with a user's best interest.
Oh-my-py unlocks max capabilities at the smartest token usage, and you can change AI company and providers while still getting things done. Roles, advisor, and the ability to use Chinese models on international providers with no training and ZDR behind OpenRouter are very powerful. You can have providers and model companies competing on price, intelligence, and speed for something that's useful but with less and less moat as model progress plateaus.
I now use GLM 5.3 for slow/planning, GLM 5.3 Flash as the default task-vision model, and DeepSeek Flash 4.1 as the advisor. Providers are ordered by cheapest at the minimum TPS I want for that model. I use it not only for coding but also as a personal assistant. I can ask it things and it gets them done automatically, like opening an issue on a repo, then having another agent ship the code, run the tests, and update master after having changed the app to autoupdate on cut release.
I can also ask it to do groceries. I use Bitwarden machine secrets and a limited virtual card connected to my phone.Something else that's very powerful is asking it to launch parallel agents to do things you know don't overlap too much.
The amount of agency we're gifted with is crazy, you can now move hundreds of hours of work with one hour of input using an open-source harness and open-weight models.
I can't wait for more competitors in the chip space, and to be able to buy models etched on silicon for even higher agency, speed, and independence.
I go on YouTube to watch humans talking, nature and music videos and get an insane amount of AI reviews, AI videos, and AI songs. What I find weird is how they end up at the top. Are people actually watching them, which is why they’re ranked so high? Or is the YouTube algorithm just being exploited? Fortunately, there are keywords that still bring back humans, but it’s so annoying.
Something I've noticed in a couple hobbies on youtube, is that the popular channels are not the ones that show up when I search. Like for cars, there ar 2 particular youtubers who show up all over search results, but amongst the car community you will never hear people talk about watching their videos.
most of them include potty training dinosaurs or monsters which shows authentic positions of such beings taking a shit, and the spectators ends up covered in or being bombarded with literal shit balls...
And know what is worse is that kids appear to prefer this to Tom and Jerry!
Me and my inner circle do watch them (even my sister-in-law, unemployed, just started to tinker with)
Can't speak for them though but when I search smt I don't really care if it is the top youtuber in my country or a random model with fake pictures, I just want to watch it
A lot of people are not stupid. Age verification is a backdoor for control. I read and did not even bother to comment, it's like yay, that horrendous thing they were trying to do now it's not applied to everyone. I'm also sorry for California, such a beautiful place and full of wonderful people. I hope it will recover one day.
A lot of people are stupid though. The law had zero age verification in it for example, but tons of breathless conspiracy theorists are claiming that's what it is about.
Model is great. Have to try with oh my py --prewalk with either Kimi as planner and GLM 5.3 as implementer or GLM 5.3 as planner and Flash as implementer.
They have a new shiny data center with Chinese GPUs, so hopefully they will be able to handle the demand. Their subscriptions are meh, in particular the Flash model has not that much usage. The other thing I wanted to try is Groq Qwen 3.8-27B at 450 tps to see if it's able to get work done faster.
I feel it's very important to play outside of the walled gardens, I feel they will pull the rug very soon, and I need to get job done while waiting hardware prices to go down...
I was using it side by side with GLM 5.3, and they were very, very similar. Also, the new zhipu 1 GW data center plus a flash(smaller?) model, can justify the 100T/day they said they were able to serve.
Pretty cool model, especially since it's not a nanny, if you want to unlock your own devices, like rooting an Android, it will happily help instead of flagging you.
Available for free via OpenRouter and Nous free tier. Also via OpenCode Go, but you have to pay a $5–$10 subscription. APIs are hammered now, so service is bumpy.
I do use Anthropic and OpenAI mostly because it costs me 1/40 and 1/50 of the api prices, which is way cheaper than Chinese subscriptions, but I’m ready to jump ship when they pull the plug. Fortunately they have nothing that forces me to keep paying them, and I don’t pay the crazy enterprise subscription costs, just the personal account prices.
I also die to be able to run the OSS setup locally to stop being spied on all the time.
For context, I averaged 10 hours a day prompting LLMs from when ChatGPT came out. At the start it was just function generation, then single file modules, then modules, and now I reason, design, implement and test with them.
An interesting thing is that with omp you can plan with a smart model and then implement with a dumber one. So for example, plan with Kimi 3.1 via OpenRouter and then implement with DSFV4 with zero data retention active, sorted by cheapest, and minimal tps accepted.
I get the people who are pissed about their cushy jobs evaporating, but if you know how to use these technologies it’s very freeing because it’s like having a company of people working for you, except they are not human so they’re not wasting their life working for you instead of using it for themselves.
You can make them do pretty much everything that is fuzzy-verifiable, you don’t have to worry about their feelings or that they won’t do what you asked them to do or stop, and you can activate them when you want at scale in parallel or not use them at all for days.
For me it’s a dream honestly. I never felt so much empowered in my life while being enabled to unlock my creativity with almost no boundaries.
reply