hellajack3d
Re:Qwen 3.8 27B is excellent, but it defaults to overthinking things
on Monday August 17, 2026 @03:51AM (#49327644)
Yes - it would seem so :)
I did make a PR to the official llama-cpp repo some time back (about a month or so), but abandoned it as there seemed to be too much community concern that the mechanism would degrade model performance... Perhaps i'll polish it up and put some effort into benchmarking and revive the project in the near future.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinking things
on Monday August 17, 2026 @03:37AM (#49327554)
I forked llama.cpp and added some crude mechanism to keep exactly this behavior under control - essentially guiding the reasoning process by injecting text strategically at specific thresholds. This was mainly put together to rein in Qwen3.6-27B, but I'd imagine 3.8 would react similarly.
Fork can be found here - https://github.com/laurencehardman/llama-mindcontrol/tree/ma...
Of course hacks like this are not perfect and may degrade performance slightly due to injected text pushing the model slightly out-of-distribution, so the string constants need to be chosen carefully - Qwen3.5's technical whitepaper does provide some guidance in this regard. The mechanism is absolutely more of a hack than a feature, and i'd imagine will be made redundant once llama.cpp supports more appropriate reasoning controls - but for now, i've found it pretty useful.
Re:Ask HN: Who wants to be hired? (August 2026)
on Tuesday August 04, 2026 @02:35AM (#49165004)
Location: Cape Town, South Africa
Remote: Yes
Wiling to relocate: Yes, for the right opportunity of course
Technologies - Python, C++, Ruby (on Rails), PostgreSQL, Llama.cpp, Inference, RAG, Unix-based systems, Embedded systems, Sensor fusion
Role(s): Senior Full Stack / ML Engineer / Manager
Resume/LinkedIn - https://www.linkedin.com/in/laurence-hardman/
Email - [email protected]
I'm Laurence - a senior engineer and manager with 10 years' experience in full-stack development roles, with significant experience as a FDE - as well as team management and advisory roles - extensive experience working with multinational clients in the financial services and insurance industries.
4.5 years' experience in AI (Conversational/Voice as well as advanced RAG systems development and implementation). Additional experience in embedded systems development and sensor fusion.
I'd love to hear what's out there - so please do feel free to reach out if you'd like a full copy of my resume or have a chat! :)
Re:Kimi-K3 Releases on HuggingFace 7/27
on Monday July 27, 2026 @04:31AM (#49066672)
So... Now we give huggingface the hug of death - right? ;)
Re:Ask HN: What Are You Working On? (February 2026)
on Monday February 09, 2026 @05:42AM (#46943787)
https://lekkervpn.co.za/
A south african wireguard-based consumer VPN service - surprisingly complex under the hood, about 6 months in the making so far!
Apple app store review is the biggest hurdle currently
Re:Windows Bluescreen and Boot Loops (update: caused by a Crowdstrike ...
on Friday July 19, 2024 @06:12AM (#41004446)
I guess this article might need some updating soon:
https://www.crowdstrike.com/resources/reports/total-economic...