Frannky

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.

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

yes

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.

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.

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 use OpenRouter. Interacting with the Google Cloud Console is pure pain.

I don't really need this model, but I needed a fast my voice to command thing, and Gemini flash 2.5 was extremely effective(low latency, high speed).

No need to go from audio to text to reasoning, just from audio to output json for running a command via adb automatically and it's working crazy good.

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.

Try glm 5.3, is very helpful.

Omp + 0x alpha is free via openrouter and opencode go

And I think they started nerfing fable too, it wasn't able to merge some prs into main, fable!