I wired it into OpenCode, an open-source coding harness similar to Claude Code and Codex. I'm using an OpenCode Zen key and a Gemini key, and together, these give me access to multiple SOTA models for free, without touching a separate dashboard for each provider. - Source: dev.to / 7 days ago

I drove it from my coding-agent with a handful of commands. - Source: dev.to / 10 days ago

Https://pi.dev/docs/latest/providers#openai-codex is specific that it "Requires ChatGPT Plus or Pro subscription". https://opencode.ai are also both specific that it's for "Plus/Pro" subscriptions. Is there some link where you saw free tier Codex use in non-official apps is allowed by OpenAI? (I have used the free tier in the official Codex app, but as you said, labs can have different rules for official vs... - Source: Hacker News / 14 days ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / about 1 month ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / about 1 month ago

Unsloth is primarily a fine-tuning tool — it makes QLoRA training 2-5x faster with 50-70% less VRAM. It does NOT run inference. For inference, use Ollama/llama.cpp/MLX. - Source: dev.to / 4 months ago

LoRA is the breakthrough that democratized fine-tuning: by training only 1% of model weights, it reduces GPU/VRAM needs by 10-100x. QLoRA takes it further — quantizing to 4 bits enables fine-tuning 65B+ parameter models on a single consumer GPU with just 3GB VRAM (Unsloth). - Source: dev.to / 5 months ago

Unsloth AI is designed to optimize large language model fine-tuning on modest hardware. It leverages efficient training algorithms to allow even GPUs with 24GB VRAM, like consumer-grade cards, to fine-tune models such as Llama 3 without massive resource demands or overheating risks. - Source: dev.to / about 1 year ago

Lot's of tools for each of those separately (RAG and fine-tuning). We're working on combining them but it's not ready yet. You don't need a big GPU cluster. Fine-tuning is quite accessible via both APIs and local tools. Some suggestions: - getkiln.ai (biased, my tool): let's you try all of the below, and compare/eval the resulting models - API based tuning for closed models: OpenAI, Google Gemini - API based... - Source: Hacker News / about 1 year ago

Install and configure Unsloth in Colab. - Source: dev.to / over 1 year ago