Jarkko Sakkinen
jarkko
Edited 20 hours ago
I would not call landstrip and opencode-landstrip as stable software just yet, but at least I've started to forget that the sandbox is active, unless it asks for a new permission.
I hit a bug in every two or three days, and the code base becoming less of a chaos i.e., all the convergence metrics are pointing to the right direction :-) Windows was quite rotten up until recent releases when I got some great feedback from an actual dog food eating Windows user.
While the most of the sandbox implementations taken the obvious container approach, I modeled a coding agent as follows:
1. A coding agent are bit like web browsers.
2. Thus, the process model for a sandbox should be modeled from a browser tab.
Based on these premises I made a Linux-container-free implementation, which protects the sensitive data with a combination of Landlock and SECOMP filters in Linux, Seatbelt (SBLT) in macOS and Win32 AppContainer framework in Windows, and adheres to Anthropic Sandbox Runtime JSON policy.
The chose approach has also many robustness benefits. E.g., nested containers are not required for CI runs.
My 3rd inference engine will land to Landstrip in foreseeable future. It will be be part of the sentinel layer for I/O, which protects the secrets even when prompt injection attacks are in effect.
#landstrip #opencode #agent #sandbox #anthropic #infosec
I hit a bug in every two or three days, and the code base becoming less of a chaos i.e., all the convergence metrics are pointing to the right direction :-) Windows was quite rotten up until recent releases when I got some great feedback from an actual dog food eating Windows user.
While the most of the sandbox implementations taken the obvious container approach, I modeled a coding agent as follows:
1. A coding agent are bit like web browsers.
2. Thus, the process model for a sandbox should be modeled from a browser tab.
Based on these premises I made a Linux-container-free implementation, which protects the sensitive data with a combination of Landlock and SECOMP filters in Linux, Seatbelt (SBLT) in macOS and Win32 AppContainer framework in Windows, and adheres to Anthropic Sandbox Runtime JSON policy.
The chose approach has also many robustness benefits. E.g., nested containers are not required for CI runs.
My 3rd inference engine will land to Landstrip in foreseeable future. It will be be part of the sentinel layer for I/O, which protects the secrets even when prompt injection attacks are in effect.
#landstrip #opencode #agent #sandbox #anthropic #infosec
0
0
0
Jarkko Sakkinen
jarkko
Microkorg was based on same DSP family as EA-1 and MS-2000 but from Microkorg's VST version you really cannot the same aliased crunch as from EA-1 :-) It's the combination of DSP but also DACs have their own flavor for the sound. EA-1 is the undisputed king of digital acid :-)
0
0
1
Jarkko Sakkinen
jarkko
Edited 2 days ago
In inference I hit to Rust bottlenecks. It is an enormous effort to make all loops error check free in order to not generate boilerplate. It's really hard to optimize against icache when using Rust TBH.
I spot all the time ".context()" (anyhow) or try-statements and similar cruft. When I work around not having to do any of these checks, inference is suddenly like 1-3% faster. This is ridiculous. Most of my time is now spent on Rust performance issues.
What I will do is to create a C library with the shared primitives (like matrices, tensors, fp16 and similar), which will then be used by ReadSeek and Goosedump to implement inference engines for Qwen3-VL-2B and GPT-OSS-20B.
I'll call this library as libcrank :-)
#ffmpeg
I spot all the time ".context()" (anyhow) or try-statements and similar cruft. When I work around not having to do any of these checks, inference is suddenly like 1-3% faster. This is ridiculous. Most of my time is now spent on Rust performance issues.
What I will do is to create a C library with the shared primitives (like matrices, tensors, fp16 and similar), which will then be used by ReadSeek and Goosedump to implement inference engines for Qwen3-VL-2B and GPT-OSS-20B.
I'll call this library as libcrank :-)
#ffmpeg
0
0
1
Jarkko Sakkinen
jarkko
Edited 2 days ago
This did not actually exist in dead simple form, so I created a tool for Landstrip testing use: https://crates.io/crates/mkwim
0
0
0
Jarkko Sakkinen
jarkko
I only vibecode or work on inference with my official slop shirt on :-)
0
0
1
Jarkko Sakkinen
jarkko
The screen cast below demonstrates ReadSeek 0.8.0 with hand-optimized inference engine for Qwen3-VL-2B. Given how shitty the CPU is (AMD Ryzen 5 PRO 4650) in this laptop, the performance is not all that bad, and it will of course only improve over time :-)
ReadSeek will retain itself as being based only on CPU inference as a core design decision; ReadSeek *is* smart but *does not* get in the way. That's why hand-optimized inference is even more so important aspect of this project.
The reasoning roots allowing to retain CUDA, Metal, unified memory and VRAM under user's full control. You can run your local models and ReadSeek will always do its job as an ubiquitous partner :-)
#pi #opencode #coding #agent
ReadSeek will retain itself as being based only on CPU inference as a core design decision; ReadSeek *is* smart but *does not* get in the way. That's why hand-optimized inference is even more so important aspect of this project.
The reasoning roots allowing to retain CUDA, Metal, unified memory and VRAM under user's full control. You can run your local models and ReadSeek will always do its job as an ubiquitous partner :-)
#pi #opencode #coding #agent
1
0
0
Jarkko Sakkinen
jarkko
Edited 7 days ago
As said in the README.md, each active task runs as a full pi --mode rpc process inside an outer Landstrip sandbox.
https://pi.dev/packages/pi-landstrip
I've as closely as possible reverse-engineered (via observation) how the process model in OpenCode works, and subagents are as close as you can get with Pi modelled to act and behave the same as they do in OpenCode. This includes even the shared configuration format, primary agents (build and plan) and pre-defined agent roles (e.g., explore in case you are familiar with OpenCode).
https://pi.dev/packages/pi-landstrip
I've as closely as possible reverse-engineered (via observation) how the process model in OpenCode works, and subagents are as close as you can get with Pi modelled to act and behave the same as they do in OpenCode. This includes even the shared configuration format, primary agents (build and plan) and pre-defined agent roles (e.g., explore in case you are familiar with OpenCode).
1
0
0
Jarkko Sakkinen
jarkko
summerselfie :---( actually i was enjoying the day .... (i'm on holiday)
1
0
3
Jarkko Sakkinen
jarkko
Edited 15 days ago
This is great example what can go wrong when blindly trusting AI output: you might by accident (or ignorance) make a slop copy of a trademarked brand: https://splice.com/
1
0
2
Jarkko Sakkinen
jarkko
"don't forget to post your loot when it arrives!".
I was a unsure how to accomplish the above task in detail, so I asked from Gemini what I need to do, and Gemini provided me brief instructions with these nice and luxury designer hashtags.
I just focused on looking hot and sexy in the selfie pic.
#Mastodon #Merch #Fediverse
I was a unsure how to accomplish the above task in detail, so I asked from Gemini what I need to do, and Gemini provided me brief instructions with these nice and luxury designer hashtags.
I just focused on looking hot and sexy in the selfie pic.
#Mastodon #Merch #Fediverse
1
0
4
Jarkko Sakkinen
jarkko
ASCII-7 at its best and TTY/VT compatible. You wouldn't believe how many hairs were ripped off drawing that world map. It's rendered directly from IANA's zone1970.tab.
Party like it's 1995 :-)
Party like it's 1995 :-)
0
0
0
Jarkko Sakkinen
jarkko
@oleksandr Sure, I just like to pinpoint these, as otherwise a typical reaction if you try to say anything bad about Rust's memory managent is like...
1
0
0
Jarkko Sakkinen
jarkko
All the br2-external packages of PUU OS as of today. It has been 4,5 months struggle so far.
#buildroot
#buildroot
0
0
1
Jarkko Sakkinen
jarkko
Early beginnings of test program for AMODE and MXMPLAY2. still in SDL window but over time will downscaled, refined and so forth to ao486/GUS FPGA core.
It's fixed point accross the board, catmull rom splines, and triangle fillers based on classic "fatmap.txt" formula :-) This is not recent program but it did not progress for months because there was a rounding error causing weird jumps with the camera.
I also need to make a track with FT2 as the whole point is to test MXMPLAY2.
It's fixed point accross the board, catmull rom splines, and triangle fillers based on classic "fatmap.txt" formula :-) This is not recent program but it did not progress for months because there was a rounding error causing weird jumps with the camera.
I also need to make a track with FT2 as the whole point is to test MXMPLAY2.
0
0
1