Absolium

I love AI and I've been a big fan of the speed of progression. But the clawdbots seem concerning. When do we decide that we need to hit the pause button and consolidate what we have for awhile? Moltbook has been very interesting, but it's turning scary

@Mike27356894 @greatestbkfacts @RemindMe_OfThis August 4th 2025

@greatestbkfacts August 4th, 2025.

I HAD NOTHING TO DO WITH THIS. I HAD NOTHING TO DO WITH THIS. I HAD NOTHING TO DO WITH THIS. I HAD NOTHING TO DO WITH THIS. I HAD NOTHING TO DO WITH THIS.

@svpino Depending on the kind of data, wouldn’t it be better to build a knowledge graph for this? As to also explain how different data is related

Everyone is building RAG applications, but nobody is talking about the data these systems use. You are delusional if you think clients will have their data sitting in a folder waiting for you to process it. Data is everywhere: in Google Drive, Dropbox, S3, Gmail, Slack, you name it. And, of course, no sane developer wants to build connections to every one of these systems. This would be suicide. I'm working with Ragie, and they released Ragie Connect to solve this problem. First, their RAG system is top-notch (they have published how they do on several RAG benchmarks), and with Connect, they made it very simple to integrate client data without having to write any code. (Well, in reality, you still have to write a few lines, but it's minimal.) Instead of developing one-off integrations for Drive, Dropbox, etc, you can use Connect to integrate with all of them and let Ragie handle authentication, authorization, and automatic data synchronization. This is a huge time saver!

@pingToven @openrouter That’s dope! Good luck! I’ve also made the career shift towards AI 😄

Excited to announce that today is my first day @openrouter! I'll be working on ops (ping me when a new model drops), support, & dev rel. If anyone is interested in trying out OpenRouter, or hoping to understand our offerings better, I'm your guy.

Project Spotlight: Ape Reunion @ApeReunion was a free mint launched back in April 2022 that drew me in on the back of their epic pixel art. They were one of the first collections to allow you to toggle between static and animated PFPS. They would soon develop full body versions that were playable in their MMO RPG. A second collection, Reunion Species, followed with all holders able to claim for free. One of the hardest working teams in Web3 and a case study in how to organically build a community from 0. The FP on these sit below 0.02. If you are looking for a great project that is worthy of your support, look no further.

@Desginerholic @cj_zZZz But if you use finetuning, I guess it’d be easier to create a RAG functionality on top, which gets a companies procedures or up to date application documentation

@Desginerholic @cj_zZZz I have created a similar usecase for a service desk in Autotask. For such a case I’d use RAG. As finetuning is a costly process and you want to have the latest tickets included in your solution. In case of finetuning you’d need to have daily or weekly finetuning

Have you fine-tuned any AI model? I know a few guys that are making 6-figures per month, Just by providing fine-tuned GPT-4o models to companies. Best part: NO Coding skills required! as OpenAI provided a proper interface to fine-tune its models. Here's a guide for you how you can fine-tune a GPT model: ✅️ Step 1: Prepare Your Training Data Collect Data: Gather input and output data from the company. Provide questions and answers in pairs as you want the model to respond: For example: Input: "What are your business hours?" Output: "We are open from 9 AM to 5 PM, Monday to Friday." Format Your Data: Save your examples in a JSON Lines file (.jsonl). Each line should have a prompt (input) and a completion (output), like this: {"prompt": "What is your refund policy?", "completion": "You can request a refund within 30 days of purchase."} Tip: Use JSON editor tools to transform text data into .jsonl data. ✅️ Step 2: Log into OpenAI Go to OpenAI’s platform. (Not ChatGPT but Dev dashboard) ✅️ Step 3: Upload Your Training File Navigate to Fine-Tuning Section in the left sidebar. Upload Data: Click the "Upload File" button and select your .jsonl file. ✅️ Step 4: Start a Fine-Tuning Job Create a Job: After uploading your file, click Create Fine-Tune. Select the base model (e.g., gpt-4o, gpt-4o-mini) to start fine-tuning. Configure Settings: You can add optional parameters like validation files or adjust the learning rate, but defaults work for most cases. Start Fine-Tuning: Click “Start Job.” The process may take some time depending on your dataset size. You can notice good results from 2M to 5M token dataset. (Also, the quality of dataset matters) ✅️ Step 5: Monitor the Progress Check Status: The fine-tuning dashboard will show the progress of your job. Once completed, you’ll see a new fine-tuned model ID. ✅️ Step 6: Use Your Fine-Tuned Model Use the new model ID in your API calls to generate responses. For example, specify your model in the API like this: {"model": "fine-tuned-model-id", "prompt": "You are a Customer Support Expert"} Test It: Try different prompts to see how well your fine-tuned model performs. OpenAI provides a playground to compare responses from multiple models. ✅️ Step 7: Evaluate and Deploy Check if the model performs as expected. Refine Data: If needed, add more examples to your dataset for better results. Once you're satisfied with results, Deploy this model in your client's application. Write a well structured system prompt. Charge $15k-$20k for your fine-tuning job. (If the data is not structured and you had to work hard on the dataset, add extra cost) Tip: First, try to train GPT-4o-mini as for most cases, this model works perfectly. It is cheaper to train and cheaper to run as compared to GPT-4o. That's it for today. I hope you like this guide. Join codeguide.dev if you haven't. It'll be the best resource for AI coding. Excited for the launch. (1450 waitlist community members in 9 days) Peace CJ

@notthreadguy Kind of dependa where you are. But generally history, beer, waffles and chocolate

what is there to do in belgium?

@beausecurity It does bring the safety of supply chains into question. Next to that it also brings me the question of what can they do with phones? Or electric cars?

@Absolium4 Yeah, plus would be extra difficult to trigger hundreds of simultaneous battery explosions instead of preplanned explosives

Seems pretty unlikely this is just a battery. Almost certainly had to be extra explosives in the pagers. The Israelis almost certainly controlled part of the supply chain here.

@mert Mulvad vpn for privacy

privacy stack signal protonmail zcash brave looking for best VPN recommendation

@levelsio How do you ensure no vulnerabilities are in your websites? As generally frameworks provide some solutions to common vulnerabilities like XSS and SQL injection

I think web development has the same opportunities There's immense amounts of overengineering with giant frameworks and libraries right now When you could just go back to the core and code things natively Try it!

@KChimaev Honestly whole team should be let go of the @ufc . At the end of the day even if you’re telling the truth (extremely unlikely) the team is a liability which lead to fans getting scammed. @danawhite

Hi guys! I would like you to pay attention to this video and get answers to all your questions in your head. Take a little of your time to clear up all misunderstandings!

@MartinShkreli @Domahhhh @cobie For context: This is on the sepolia test chain, with 2 test wallets of myself. *this is not on the ethereum network* Before it's usable it should be audited and gas optimized @0xQuit @PopPunkOnChain

@MartinShkreli @Domahhhh I spun up a quick escrow smart contract for this. Everyone can contribute, if you're right, you get everything. If they're right they get everything proportionally. @cobie can be the controller. Check it out: #code" target="_blank" rel="nofollow noopener">sepolia.etherscan.io/address/0x1f14…

as defined, this is literally 100% chance

@HDRobots @IAmPascio Hey! That sounds cool, would you mind having a chat about it?

@IAmPascio Nice to e-meet you Pascio. I'm Kris, a UX Researcher and AI enthusiast.

Have less than 1,000 followers? Introduce yourself in 1 sentence. Let's follow you right now.

@IAmPascio I’m an eternal student, currently working on AI and helping businesses use AI to support their operations