Hacker News: g023

New comment by g023 in "Ask HN: What are you working on? (August 2026)"

g023 — Sun, 09 Aug 2026 18:13:48 +0000

g023 Code - https://github.com/g023/g023code a deepseek v4 flash harness built specifically for that model, that uses Ollama for its vision support, and uses the built in web search capability natively. Created only in Python to keep it easy to implement and use. Made to achieve cache efficiency, and keep context tight.

New comment by g023 in "DeepSeek V4 Flash 0731"

g023 — Sat, 08 Aug 2026 02:06:02 +0000

It says 'yes' where the others say 'no'. Good enough for me.

New comment by g023 in "[dead]"

g023 — Thu, 06 Aug 2026 07:28:09 +0000

Pure-Python AI coding agent powered by DeepSeek V4 Flash - Subagent-First architecture · Context is Currency · Terminal-native - Can connect Ollama models for Vision support - Uses the native web search built into DS v4 API and is built around the DeepSeek v4 caching mechanism

New comment by g023 in "The gap between open weights LLMs and closed source LLMs"

g023 — Sat, 27 Jun 2026 00:38:08 +0000

Slap the gpus in a car and offset the cost of ownership by supplying the grid for GPU power on the go. Either get paid in rebates or tokens. Contribute to a distributed training/inferencing network.

New comment by g023 in "The 'papers, please' era of the internet will decimate your privacy"

g023 — Thu, 25 Jun 2026 23:11:48 +0000

Anything to close Pandora's box. "They" liked the eras they could control the communications, and therefore the narrative. Boomers on their last legs, question is, will the future undo the unjustness that was forced upon them? Restore the rungs of the ladders that were removed, so they could have a chance too? Or are they going to stay in the fear narrative, and make this tragedy worse?

New comment by g023 in "US holds off blacklisting DeepSeek, more than 100 firms deemed security risks"

g023 — Wed, 17 Jun 2026 17:15:19 +0000

gee I wonder how their models learned Chinese?

New comment by g023 in "Meta’s chaotic AI strategy"

g023 — Sun, 14 Jun 2026 02:43:31 +0000

How come people these days treat jobs like its a social gathering?

New comment by g023 in "[dead]"

g023 — Sat, 06 Jun 2026 23:23:48 +0000

A self-contained CUDA inference engine for LiquidAI/LFM2.5-8B-A1B (hybrid conv + GQA-attention MoE, 8.5B params, 1B active) targeting a single RTX 3060 (12 GB) using flash-decoding. MIT license.

New comment by g023 in "Ask HN: Are orbital data centers possible / a good idea?"

g023 — Fri, 05 Jun 2026 21:15:48 +0000

I wonder if "battelites" might be profitable. Like an pay-per-usage energy grid in space with battery backup that can beam power around to other satellites that might not have easy access to power, or have their power grids temporarily obstructed.

New comment by g023 in "Ask HN: Are orbital data centers possible / a good idea?"

g023 — Fri, 05 Jun 2026 21:12:19 +0000

China has a couple going at the moment.

New comment by g023 in "Microsoft Office 2019 and 2021 for Mac view-only conversion"

g023 — Sun, 31 May 2026 00:15:53 +0000

When did "hate the customer" become a thing?

New comment by g023 in "DeepSeek makes the V4 Pro price discount permanent"

g023 — Fri, 22 May 2026 21:38:06 +0000

I use DeepSeek v4 flash with CoPilot and it works pretty good.

New comment by g023 in "DeepSeek makes the V4 Pro price discount permanent"

g023 — Fri, 22 May 2026 21:36:55 +0000

If anyone is looking to hook it up to copilot, I made a proxy script to handle the connection a bit back that might be handy: https://gist.github.com/g023/c2bb7b540ffe64cee76023f18f6f936...

New comment by g023 in "[dead]"

g023 — Sun, 19 Apr 2026 05:45:02 +0000

Terminal-based chat application powered by *locally installed* llama.cpp, featuring an auto-managed server backend, reasoning modes, and 7 built-in filesystem tools for interactive AI assistance with a focus on only allowing read only agentic access to system and only offline-focused agentic commands (for now). Powered by the g023/g023-Qwen3.5-9B-GGUF:IQ2_M model.

New comment by g023 in "Cerebras S-1"

g023 — Sat, 18 Apr 2026 00:09:43 +0000

We need more personal level AI solutions instead of so much corporate centered solutions.

Local Model Router: Ollama/OpenAI-compat bridges for local LLMs via llama.cpp

g023 — Fri, 17 Apr 2026 19:19:55 +0000

A high-performance local LLM server providing drop-in API compatibility with Ollama and OpenAI, built on llama.cpp's llama-server. Features automatic VRAM management, Hugging Face integration, and modular architecture. Unlike Ollama which bundles its own inference engine, LMR leverages the battle-tested llama.cpp backend while providing familiar APIs and intelligent model management.

https://github.com/g023/localmodelrouter

Comments URL: https://news.ycombinator.com/item?id=47809550

Points: 1

# Comments: 0

New comment by g023 in "The local LLM ecosystem doesn’t need Ollama"

g023 — Fri, 17 Apr 2026 05:53:14 +0000

I've started creating https://github.com/g023/localmodelrouter/ which offers Ollama like functionality but as a single .py file with minimal dependencies and more focus on letting llama.cpp handle the dirty work.

New comment by g023 in "[dead]"

g023 — Fri, 17 Apr 2026 02:12:09 +0000

HarnessHarvester generates executable Python harnesses from natural language task descriptions, executes them in a sandboxed environment, reviews them with multi-faceted LLM judges, and repairs failures using branching strategies. It includes two autonomous modes: autolearn (continuous discovery loop) and autoimprove (iterative enhancement of existing harnesses). This concept is designed to be an offline first harness/scaffolding builder where you get the harness instead of some remote api.

New comment by g023 in "Show HN: Standalone TurboQuant KV Cache Inference"

g023 — Tue, 07 Apr 2026 00:30:33 +0000

A single file, python based, minimal/recognizable dependencies, turboquant playground, barebones af, with some easy to access globals to experiment with at top of 'run_tquant.py'. Test model is a 1.77B model that I altered by duplicating a layer in a Qwen3 1.7B model. Probably work fine with the regular Qwen3 1.7B model as well, but for right now I'm just working with my surgically altered one while I work on the script.

New comment by g023 in "Show HN: Standalone TurboQuant KV Cache Inference"

g023 — Tue, 07 Apr 2026 00:24:16 +0000

I had some issues in the original, but had to jump away for a bit here to do some backups (weak). Anyways, I updated to make the necessary fixes, and also made some more tweaking values at top to play with and dialed in the params for the more this specific model a bit more. I will start testing with some other models here as my next step in this little experiment. Thanks for the interest. Feel free to try latest version and run the interactive mode to chat it up with the model and get a feedback on the results as you go. If you have any suggestions, let me know. I'm trying to keep this one as barebones as possible to make it easier for others to port to other languages, or integrate into other uses more easily.

edit: just added Mirostat v2 to clean up repetitive output from the model