Developer Advice

Every developer you admire started with nothing.

No GitHub profile. No experience. No reputation. Just curiosity and the decision to keep going.

Some built tools no one asked for.

Some spent nights debugging problems no one else could solve.

Some kept learning when it would've been easier to settle.

But none of them waited to be chosen.

They chose themselves.

The breakthrough didn't come after they became "good enough."

It came because they showed up before they felt ready.

You don't need someone to validate your skills.

You need to start building with what you have.

In tech, you don't get ahead by waiting.

You get ahead by doing.

Comments

🔰 23 Important Commands in the RUN (Executer) List 🔹 The command dxdiag: Used to check all the specifications of your device. 🔹 The command cleanmgr: Opens the Disk Cleanup tool. 🔹 The command temp: Accesses temporary files, which we delete as they contribute to slowing down the computer. 🔹 The command regedit: Opens the Registry Editor. 🔹 The command calc: Opens the Calculator. 🔹 The command msconfig: A tool to access programs that run with Windows at startup and disable them to speed up the system. 🔹 The command scandisk: Used for disk checking. 🔹 The command cmd: Opens the Command Prompt for Windows. 🔹 The command defrag: Used to stop and defragment the hard drive. 🔹 The command taskman: Allows you to see what is open in the taskbar and manage it. 🔹 The command pbrush: Opens the Paint program in Windows. 🔹 The command debug: Used to ch...

Is it the end of lora?

Is this the end of LoRA as a fine-tuning approach? Singular Value fine-tuning is here! We have a new paper in town called the "Transformers Squared". It promises to adapt any LLM to any task without external intervention. The core idea of the paper is to use Singular Value Decomposition (SVD) to factorize the weight matrices of transformers. During training, we learn different singular values for different tasks. More specifically, we learn to scale the singular values for different tasks. Tasks can be as diverse as math reasoning or coding. The possibilities are endless. During inference, we do a two-pass inference. In the first pass, the LLM decides which "scale" to use for which task. In the second pass, the LLM adapts itself to be a specialist in the task and responds to our prompt. How cool is that? Paper Title: Transformer2: Self-adaptive LLMs Paper: https://sakana.ai/transformer-squared Blog: https://arxiv.org/abs/2501.06252 Video Explanation: https://youtu...

TECH AND SCIENCE CONTENT BELOG.

Search This Blog