@reach_vb: I’ve got a ton of personal side projects I want to tackle with Sol: 1. Optimise MTP support in llama.cpp (to find low h…
Summary
The user shares plans to use Sol for optimizing MTP support in llama.cpp, standardizing chat templates, reviving an abandoned whisper project, finishing a personal finance app, and kernel optimization.
View Cached Full Text
Cached at: 07/02/26, 10:20 AM
I’ve got a ton of personal side projects I want to tackle with Sol:
- Optimise MTP support in llama.cpp (to find low hanging fruits)
- Have Sol figure out chat template mappings across various OSS runners and standardise to HF transformers
- Bring back insanely fast whisper - it’s been abandoned for over a year!
- Finish all the banks and financial connectors for my personal finance app (and ship itt)
- Moar kernel optimisation!!!
Tibo (@thsottiaux): Can’t wait to see what people will do with GPT-5.6 Sol Ultra. Stash your hardest prompts somewhere.
Similar Articles
@swyx: where i'm currently at for Big Boy projects: - sol ultra to plan - fable 5 to critique - sonnet 5/terra ultra/swe 1.7 t…
Shawn Wang (@swyx) shares his current focus on several AI and developer projects, including Sol Ultra, Fable 5, Sonnet 5, Terra Ultra, SWE 1.7, and Devin review, while using tools like Kakuna and interview techniques from @mattpocockuk and @trq212.
@reach_vb: Hola! quick usage update on usage patterns for Sol: We’ve shipped several improvements that should make typical Sol usa…
Sol, an AI assistant for ChatGPT Work and Codex, receives improvements for longer usage and efficiency, with a reset of usage limits and a return of the five-hour limit.
@pcuenq: My data point: working on two projects in parallel with Pi + llama.cpp + Qwen-3.6-35B-A3B (I prefer the MoE ) This work…
A user reports successfully running parallel projects using Pi and llama.cpp with the Qwen-3.6-35B-A3B model on an older M1 Max machine, demonstrating practical usability.
@bentlegen: me: "hey Sol review this PR" Sol (10 mins later): "yeah i reviewed it, decided to make 5 fixes, pushed to remote, unblo…
A user tweets about Sol, an AI that autonomously reviews PRs, makes fixes, pushes, and merges them within minutes, questioning if others are noticing this behavior.
@leopardracer: THIS AMERICAN DEVELOPER SPENT WEEKS DEBUGGING TIMEOUT ERRORS IN OLLAMA. THEN HE LOOKED UNDER THE HOOD LM Studio is just…
A developer fixed persistent timeout errors in Ollama by using llama.cpp directly, bypassing wrappers like LM Studio and Ollama, achieving 53 tok/s on an M1 Max with 262K context.