Richard Palethorpe
@richiejp.com
I wrote a kernel exploit for an n-day once.
I added transcription prompts to LocalAI's Whisper backend and immediately put it to use in VoxInput. This means that when I say "LocalAI" and "VoxInput", it actually transcribes those correctly. Also works great with OpenAI.
github.com/mudler/Local...
github.com/richiejp/Vox...
github.com/mudler/Local...
github.com/richiejp/Vox...
feat(whisper): Add prompt to condition transcription output by richiejp · Pull Request #7624 · mudler/LocalAI
chore(makefile): Add buildargs for sd and cuda when building backend feat(whisper): Add prompt to condition transcription output Description Allows the user to add previously transcribed text or s...
github.com
December 18, 2025 at 4:46 PM
I added transcription prompts to LocalAI's Whisper backend and immediately put it to use in VoxInput. This means that when I say "LocalAI" and "VoxInput", it actually transcribes those correctly. Also works great with OpenAI.
github.com/mudler/Local...
github.com/richiejp/Vox...
github.com/mudler/Local...
github.com/richiejp/Vox...
I released VoxInput v0.5.0 which now has a GUI that notifies you when VoxInput begins or stops listening for voice audio to transcribe.
July 16, 2025 at 3:46 PM
I released VoxInput v0.5.0 which now has a GUI that notifies you when VoxInput begins or stops listening for voice audio to transcribe.
I watched Karpathy's excellent Micrograd video and implemented the Micrograd library in Go. Today I recorded some of my thoughts on the differences between the original Python and my Go implementation: www.youtube.com/watch?v=76DB...
July 9, 2025 at 8:36 AM
I watched Karpathy's excellent Micrograd video and implemented the Micrograd library in Go. Today I recorded some of my thoughts on the differences between the original Python and my Go implementation: www.youtube.com/watch?v=76DB...
I added real-time voice transcription to VoxInput by implementing the transcription only mode for OpenAI's real-time transcription API in LocalAI.
youtu.be/Ims16LC_Bp8
youtu.be/Ims16LC_Bp8
VoxInput/v0.4.0/Realtime Transcription
Demonstrating realtime transcription that uses LocalAI's implementation of the OpenAI realtime API.https://github.com/mudler/LocalAI/pull/5392https://github....
youtu.be
May 26, 2025 at 3:46 PM
I added real-time voice transcription to VoxInput by implementing the transcription only mode for OpenAI's real-time transcription API in LocalAI.
youtu.be/Ims16LC_Bp8
youtu.be/Ims16LC_Bp8
I created a voice transcription agent for Linux that works with any Linux desktop and uses OpenAI's and therefor LocalAI's API to transcript audio with Whisper.cpp. It can input text anywhere because it uses a virtual keyboard via dotool
github.com/richiejp/Vox...
github.com/richiejp/Vox...
GitHub - richiejp/VoxInput: Transcribe input from your microphone and turn it into key presses on a virtual keyboard. This allows you to use speech-to-text on any application or window system in Linux. In fact you can use it on the system console.
Transcribe input from your microphone and turn it into key presses on a virtual keyboard. This allows you to use speech-to-text on any application or window system in Linux. In fact you can use it ...
github.com
May 9, 2025 at 8:36 AM
I created a voice transcription agent for Linux that works with any Linux desktop and uses OpenAI's and therefor LocalAI's API to transcript audio with Whisper.cpp. It can input text anywhere because it uses a virtual keyboard via dotool
github.com/richiejp/Vox...
github.com/richiejp/Vox...
Mudler merged my triggers and filters feature into LocalAGI: youtu.be/d_we-AYksSw?...
Not much interest in IRC though, maybe I should upgrade to Matrix?
Not much interest in IRC though, maybe I should upgrade to Matrix?
LocalAGI/V2/AI powered IRC bot/Filters feature
Shows the configuration for an AI power IRC bot that only responds to messages of a particular type.This shows a feature I am currently working on called Fil...
youtu.be
May 6, 2025 at 3:46 PM
Mudler merged my triggers and filters feature into LocalAGI: youtu.be/d_we-AYksSw?...
Not much interest in IRC though, maybe I should upgrade to Matrix?
Not much interest in IRC though, maybe I should upgrade to Matrix?
I made a little update to LocalAGI's action playground that creates a form for action configuration and parameters, this saves you having to enter raw JSON. The Action Playground is for testing actions when the agent has issues making tool calls.
April 28, 2025 at 3:46 PM
I made a little update to LocalAGI's action playground that creates a form for action configuration and parameters, this saves you having to enter raw JSON. The Action Playground is for testing actions when the agent has issues making tool calls.
LocalAGI: Create and run AI agents locally without writing code
LocalAGI: Create and run AI agents locally without writing code
LocalAGI allows you to create "AI agents" that run completely on your hardware and can access your systems to perform tasks. It's Open Source, allowing you to self-host, modify and audit it.
www.linkedin.com
April 19, 2025 at 3:46 PM
LocalAGI: Create and run AI agents locally without writing code
Never say that we don't still make shit in the UK!
April 15, 2025 at 3:46 PM
Never say that we don't still make shit in the UK!
A lot of the frictions to running AI locally are just generic software configuration issues. Basically there is a GPU involved which is a different kind of architecture and comes with its own software stack. Each vendor has there own stack and there are a whole bunch of combinations of software and
April 14, 2025 at 3:46 PM
A lot of the frictions to running AI locally are just generic software configuration issues. Basically there is a GPU involved which is a different kind of architecture and comes with its own software stack. Each vendor has there own stack and there are a whole bunch of combinations of software and
In this weeks news letter I wrote/ranted about the process of supporting Intel GPUs in LocalAI with SYCL. Essentially it's *just* a case of getting the software to build and that boils down to passing the right flags to the compiler. 1/2
Enabling Intel GPUs with GGML's SYCL support in LocalAI, how hard can it be?
LocalAI has at least two backends that support Intel's SYCL. One is Llama.
www.linkedin.com
April 13, 2025 at 3:46 PM
In this weeks news letter I wrote/ranted about the process of supporting Intel GPUs in LocalAI with SYCL. Essentially it's *just* a case of getting the software to build and that boils down to passing the right flags to the compiler. 1/2
If you vibe code a SaaS app, the second it makes money that should be reinvested into paying someone to clean it up. Coding agents are incredible, but so far I have not seen any which do penetration testing and vibe coding produces a large attack surface.
April 5, 2025 at 8:36 AM
If you vibe code a SaaS app, the second it makes money that should be reinvested into paying someone to clean it up. Coding agents are incredible, but so far I have not seen any which do penetration testing and vibe coding produces a large attack surface.
I've lost so much time over my career to simple build errors buried in piles of awkward software. Often the error manifests at runtime as something completely baffling and terrifying. At the end it turns out to be typo which would be completely avoidable with some static checking.
April 3, 2025 at 3:46 PM
I've lost so much time over my career to simple build errors buried in piles of awkward software. Often the error manifests at runtime as something completely baffling and terrifying. At the end it turns out to be typo which would be completely avoidable with some static checking.
It's incredible that vibe coding is even a thing and my son is going to grow up thinking it's normal to speak to computers in natural language.
April 3, 2025 at 8:36 AM
It's incredible that vibe coding is even a thing and my son is going to grow up thinking it's normal to speak to computers in natural language.
Most people think an AI agent is a person who does something with AI. Not an automation that combines LLMs and other algorithms to give the appearance of agency.
April 2, 2025 at 8:36 AM
Most people think an AI agent is a person who does something with AI. Not an automation that combines LLMs and other algorithms to give the appearance of agency.
Let's say that the stories about software dev teams being let go due to AI are true; I don't see this situation lasting for long. Every previous advance in software technology has lead to greater penetration by software into every aspect of industry. There is then more demand for coders, because
April 1, 2025 at 3:46 PM
Let's say that the stories about software dev teams being let go due to AI are true; I don't see this situation lasting for long. Every previous advance in software technology has lead to greater penetration by software into every aspect of industry. There is then more demand for coders, because
In this week's newsletter I vibe coded a "bare metal" program that runs inside a Firecracker micro VM on x86_64 and accepts commands through the serial terminal.
So yes kernel developers, you are not safe either!!!
So yes kernel developers, you are not safe either!!!
Vibe coding an OS kernel into existence
I've been trying out Windsurf, which is a competitor to Cursor. I found that it's rather good, so I thought to myself, what's the most absurd thing I can try to code just using AI? In other words,…
www.linkedin.com
March 25, 2025 at 4:46 PM
In this week's newsletter I vibe coded a "bare metal" program that runs inside a Firecracker micro VM on x86_64 and accepts commands through the serial terminal.
So yes kernel developers, you are not safe either!!!
So yes kernel developers, you are not safe either!!!
Often we want to know which process is using our bandwidth and where it is sending data to. This can be done with Dinko Korunic's pktstat-bpf utility which I added CGroups support to this week.
Tracking bandwidth usage per process with eBPF and CGroups
Finding which process are sending receiving data with a given host appears to be a common need and here are some of the reasons I have seen for it: Preventing data usage charges on cellular networks…
www.linkedin.com
March 14, 2025 at 9:36 AM
Often we want to know which process is using our bandwidth and where it is sending data to. This can be done with Dinko Korunic's pktstat-bpf utility which I added CGroups support to this week.
AI coding tools are reshaping development: I built an IRC bridge and a Go web app with minimal effort using Avante for Neovim. Will these tools replace developers or make skilled coders more valuable? My hands-on experience with Avante, Cursor, and Bolt[.]new reveals their promise and limitations.
Avante, Bolt.new and Cursor: coding tools that are going to replace me next year
In this weeks issue: Avante is a great tool for bringing AI to Neovim. Also a comparison with Cursor and Bolt.
buff.ly
March 7, 2025 at 4:46 PM
AI coding tools are reshaping development: I built an IRC bridge and a Go web app with minimal effort using Avante for Neovim. Will these tools replace developers or make skilled coders more valuable? My hands-on experience with Avante, Cursor, and Bolt[.]new reveals their promise and limitations.
This is pure cringe, but I have started making videos from my Newsletter:
Techbits week 9: Configuration control with NixOS and Kairos. Tools: blxrep, udpspeeder and more
In this weeks issue!Configuration control with NixOS and KairosTools: blxrep, udpspeeder, Node-RED, RAG and belowRandom: LTE/5G vulnerabilities and Mr. Beast...
buff.ly
March 1, 2025 at 4:46 PM
This is pure cringe, but I have started making videos from my Newsletter:
This weeks newsletter:
Week 9: Configuration control with NixOS and Kairos. Tools: blxrep, udpspeeder and more
In this weeks issue! Configuration control with NixOS and Kairos Tools: blxrep, udpspeeder, Node-RED, RAG and below Random: LTE/5G vulnerabilities and Mr. Beast Configuration control with NixOS and…
buff.ly
February 28, 2025 at 4:46 PM
This weeks newsletter:
The 4th issue: Internet of Tractors: What language does farm equipment speak? How not to write web app: Should have used Pocketbase, Avoid upset by understanding the 3 types of OSS
Week 8: What language does farm equipment speak? Should have used Pocketbase and the 3 types of OSS
In this week's issue, which is issue 4: Internet of Tractors: What language does farm equipment speak? How not to write web app: Should have used Pocketbase Avoid upset by understanding the 3 types…
buff.ly
February 21, 2025 at 4:46 PM
The 4th issue: Internet of Tractors: What language does farm equipment speak? How not to write web app: Should have used Pocketbase, Avoid upset by understanding the 3 types of OSS
I'm releasing a text only version of my LinkedIn newsletter on my website as a backup
richiejp.com#newsletter
richiejp.com#newsletter
Richard Palethorpe’s Index
Richard Palethorpe’s
(Software Engineer) website index
richiejp.com
February 21, 2025 at 3:49 PM
I'm releasing a text only version of my LinkedIn newsletter on my website as a backup
richiejp.com#newsletter
richiejp.com#newsletter
This week: Spy on what data a process reads or writes with eBPF, make your app better with Unikernels and my 2c's on WASM.
Week 7: Spying with eBPF, WASM shouldn't exist, Go fast with Unikernels and tools
In this weeks issue Spying on packets and processes with eBPF Why WASM shouldn't exist Can your app run in a Unikernel? Tools: Computer engineering for Babies, AstroVim and Gitu Using eBPF to spy on…
buff.ly
February 14, 2025 at 4:46 PM
This week: Spy on what data a process reads or writes with eBPF, make your app better with Unikernels and my 2c's on WASM.