Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
28 contributions to Build Market Close
113 Decision Models in 3 Weeks!!! 70 from 2 open weights models
Anyone curious about Decision Models?? I spent some time this week digging in to the details. Unbelievable proliferation in 3 weeks. https://opendoorlearningai.com/articles/113-decision-models-in-3-weeks/ TL;DR - A decision model takes some evidence plus closed questions and returns typed answers with probabilities. It writes no prose. A decision costs a tiny fraction of a cent and comes back in tens to hundreds of milliseconds. - One request can carry many questions. They run in parallel and independently, so nothing chains inside a call. - “113 entries” overstates the variety. 70 of the 112 open entries are built on Qwen, 18 on Gemma 4, and 20 are stock models with a decoding trick and no new weights. - On the independent Decision Index, Perplexity Decider v1.1 ranks first on its own, and Fastino GLiDE, Jev and Torchcast tie for second. Calibration, price and where you can run it separate the leaders more than accuracy does. - Measured fairly, the 27B models answer in 0.10 to 0.14 s on one local GPU, and hosted APIs timed by independent testers mostly land between 0.1 and 0.6 s. - Laya is one of the weakest open options. Every hardware tier, down to a laptop, has open models scoring 6x to 14x higher. - My proposed inbox setup: one script polls, filters, asks for four facts per email and applies rules, and the LLM runs only for mail that needs writing. Estimated $353 a month down to $28. It isn’t running yet; results will follow in a separate article.
3 likes • Oct 11
Subscribed! Thank you.
I'm banned from Clief Notes
Not sure why I was... but tagging me over there won't work anymore 🙃 Onward and upward, frens' Always got your back, RyMac
I'm banned from Clief Notes
1 like • Oct 9
@Jordan Shaw
1 like • Oct 9
@Ry Mac kid sh#t 😩 the admin needs to grow up bc that is a seriously immature move.
Live Build: A SMB's Website + Business OS (ICM)
The longest live build to date that I've made public. I turned on my screen and launched a client's (mechanic shop): -Website (Design -> research -> launch) -Added an optimized blog -Created their gameplan to gain clients without waiting on the internet - Built my internal ICM to manage the process -Built the ICM they will manage their business with (the business OS) -Riff'ed random things along the way It's 1 hour and 44 minutes long with Fred speeding things up for us. -> https://www.youtube.com/watch?v=M9Crh412QAc Questions? Always got your back, RyMac P.S. There are no edits or "takes", it's just me launching a SMB's website the way I have for 15+ years but now it takes 2 hours instead of 2 weeks. The classroom: #Watch Me Build & Launch A Client Website + ICM OS
1 like • Oct 6
😳🤯
7 Step Framework To Closing Deals
Let's fix it. Look, sales isn't something you can perfect without doing it and it's definitely not a "script". It's a framework. Just like the things you build...there are steps to follow. ICM is a framework. There are a few moments that really matter in your framework in sales. 1) The trust frame is a sentence (and the story of a lady patching in her son from jail during a sales call) 2) The only time "no" means "yes" 3) The presentation is a map + calculator not the whizbang 4) Temperature testing = the truth 5) The moment you shut up buttercup 6) The 3 ways to handle any and all objections I think @Darren Soares is the only one who's went through the free sales training in the classroom. Maybe since it's on the Tubez, you will too? Always got your back, RyMac P.S. The same training broken down into micro lessons is here in the classroom. P.P.S BMC' App is getting really close to launching. Premium, VIP, and people on the waiting list get the beta deal I talk about on the page. There's an example of me live sparring there, too. P.P.P.S Fred Built The Perfect ICM Builder just in case you haven't seent' it.
1 like • Oct 6
Two people you never lie to 😆
I gave the same plan to 1 AI model and to a team of 4. Solo missed it.
I had a plan I cared about, so I didn't want just 1 opinion on it. I set up a Mixture of Agents team in Hermes: 3 models advising, 1 making the call. Then I gave the exact same plan to a single model. The single model said my routing was sound. The team found the hole. My plan assumed the assets it needed already existed, and nothing said when a job was actually done. Nothing breaks on day 1 with a gap like that. It just drifts. Getting it running took me 2 failed runs and about 45 minutes. I put the fix and 4 prompts you can run on your own plan in the classroom: https://www.skool.com/buildmarketclose/classroom/9a11fe1b?md=cf1ccecdcc85477089743af1ad4d154a Read the Blog ------>https://agentsasfolders.ai/blog/hermes-agent-tutorial-1-folder-4-files/ What's 1 plan in your business you'd want a second opinion on before you build it?
2 likes • Oct 6
This was helpful to watch and combine different llm’s. A programmer friend just put me onto glm5.3 so I am going to use this to play around and incorporate it into my workflow. I do a little programming and I’m currently linking my working projects to supporting resources (my writing, pdfs, md files, etc) and also some of the philosophy behind it (nutrition and exercise research, mentor notes, textbooks, etc). Thanks for sharing this!
1-10 of 28
Miguel Alemar
4
57 points to level up
@miguel-alemar-1057
Sports Nutritionist & Strength Coach

Active 1d ago
Joined Aug 21, 2026
Powered by