bachittle
Joined 2 years ago
Karma
94
Submissions
38
Member since
Dec 6
Recent submissions
Comment · 1 month ago
The exploit is a local zero day exploit, meaning the machine needs to already be compromised. For it to be a remote zero day exploit you need to do the ClickFix attack. The idea is that it lets you access much more machines and resources if the one machine with Muse is compromised. More info here: https://x.com/dps/status/2102248329111634067
Comment · 3 months ago
...and then scroll down a few lines and you will find tons of em-dashes in the AGENTS.md
Comment · 4 months ago
this looks cool for game development, because using Git for projects in Unity and Unreal Engine definitely has it's issues. I'm personally not a fan of Git LFS, especially since GitHub charges you to use it (which makes sense, binaries and assets are big, code is small, relatively speaking).
Comment · 4 months ago
Exactly this, and this tool called qmd is what I use for the hybrid search portion. It also uses local LLMs to provide summaries on your own markdown data too. My agents use both depending on what type of search they are doing, and both provide good results.
Comment · 6 months ago
So Opus 4.7 is measurably worse at long-context retrieval compared to Opus 4.6. Opus 4.6 scores 91.9% and Opus 4.7 scores 59.2%. At least they're transparent about the model degradation. They traded long-context retrieval for better software engineering and math scores.
Comment · 7 months ago
Did you also try Forgejo? If so, what are the differences between the two? I didn't even know GitLab had a self-hosted option. I assume it's probably better for Enterprise-grade projects, and dealing with CI/CD, actions, etc. But for smaller projects that just have issues and PRs and minor test suites, I assume Forgejo is the better lightweight option.
Comment · 7 months ago
I have enjoyed using Forgejo over GitHub for local work. The features that GitHub has that plain Git does not includes a nice web renderer of markdown and code, issues and pull requests with comments, and project kanban boards. It's nice to have an alternative for local usage if GitHub ever goes down or just for private projects. Especially nice with agentic workflows, because agents can port issues, PRs, etc. back and forth between GitHub and Forgejo.
Comment · 7 months ago
Coqui TTS is actually deprecated, the company shut down. I have a voice assistant that is using gpt-5.4 and opus 4.6 using the subsidized plans from Codex and Claude Code, and it uses STT and TTS from mlx-audio for those portions to be locally hosted: https://github.com/Blaizzy/mlx-audio
Here are the following models I found work well:
- Qwen ASR and TTS are really good. Qwen ASR is faster than OpenAI Whisper on Apple Silicon from my tests. And the TTS model has voice cloning support so you can give it any voice you want. Qwen ASR is my default.
- Chatterbox Turbo also does voice cloning TTS and is more efficient to run than Qwen TTS. Chatterbox Turbo is my default.
- Kitten TTS is good as a small model, better than Kokoro
- Soprano TTS is surprisingly really good for a small model, but it has glitches that prevent it from being my default
But overall the mlx-audio library makes it really easy to try different models and see which ones I like.
Comment · 7 months ago
If you want your comments to sound more human — stop using em dashes everywhere. LLMs love them — along with neat structure, “furthermore”-style transitions, and perfectly balanced paragraphs.
Humans write a bit messier — commas, short sentences, abrupt turns.
Comment · 8 months ago
The RTX 5090 only has 32gb of VRAM. So the tradeoff is NVIDIA is for blazing speed in a tiny memory pool, but Apple Silicon has a larger memory pool at moderate speed.
Comment · 8 months ago
I'm running a local voice agent on a Mac Mini M4. Qwen ASR for STT and Qwen TTS on Apple Silicon via MLX, Claude for the LLM. No API costs besides the Claude subscription but the interesting part is the LLM is agentic because it's using Claude Code. It reads and writes files, spawns background agents, controls devices, all through voice.
The insights about VAD and streaming pipelines in this thread are exactly what I'm looking at for v2. Moving to a WebSocket streaming pipeline with proper voice activity detection would close the latency gap significantly, even with local models.
Comment · 8 months ago
Do you think it would be possible in the future to maybe add developer settings to enable or disable certain features, or to switch to other sandboxing methods that are more lightweight like Apple seatbelt for example?
Comment · 8 months ago
OpenAI Codex CLI was able to use it effectively, so at least AI knows how to use it. Still, its deprecated and not maintained, Apple needs to make something new soon.