Hacker News: syntaxing

New comment by syntaxing in "BYOMesh – New LoRa mesh radio offers 100x the bandwidth"

syntaxing — Sun, 03 May 2026 22:58:56 +0000

Yeah, openmanet with reticulum seems the most “professional” right now

New comment by syntaxing in "BYOMesh – New LoRa mesh radio offers 100x the bandwidth"

syntaxing — Sun, 03 May 2026 19:29:10 +0000

I’m guessing it’s just haloW without the licensing requirements.

New comment by syntaxing in "BYOMesh – New LoRa mesh radio offers 100x the bandwidth"

syntaxing — Sun, 03 May 2026 19:26:50 +0000

It sucks how everything feels like a toy. I think meshtastic is the closest thing to a “product”. They made a bunch of bad architectural decisions that are haunting them now like how nodes broadcast its info.

New comment by syntaxing in "BYOMesh – New LoRa mesh radio offers 100x the bandwidth"

syntaxing — Sun, 03 May 2026 19:21:56 +0000

I know it’s all open source and I’m not paying for anything so I cant be choosy. But after playing with a bunch of Lora peer to peer chat systems. All I wish is a chat service that uses haloW. Since it uses wifi backend, regular wifi should work as well.

New comment by syntaxing in "American Dads Became the Parents Their Fathers Never Were"

syntaxing — Thu, 30 Apr 2026 20:22:05 +0000

Dad and millennial here and this change has been very noticeable in my circle of friends including myself and I’m all for it. Men have been doing their share of housework too. But I will say, it’s not all dads but enough that I think this will have a positive effect on the next generation.

New comment by syntaxing in "Mike: open-source legal AI"

syntaxing — Thu, 30 Apr 2026 03:17:47 +0000

I always wondered if Justin Kan’s Atrium closed door prematurely by just 2-3 years. It would have been cool to see a “technology” driven law firm and how it would have adjusted to LLMs.

New comment by syntaxing in "Mistral Medium 3.5"

syntaxing — Wed, 29 Apr 2026 19:22:03 +0000

With turbo quant, you would reduce it by over 6X.

New comment by syntaxing in "Mistral Medium 3.5"

syntaxing — Wed, 29 Apr 2026 17:00:20 +0000

This is a very interesting strategy that might pay off. This model is a very good option for enterprise self host. I would argue a lot of companies are VRAM constrained rather than compute constrained. You could fit 4-5 running instances on one H100 cluster where you can only fit 1-2 Kimi K2 or GLM5.

New comment by syntaxing in "We decreased our LLM costs with Opus"

syntaxing — Wed, 29 Apr 2026 03:00:37 +0000

Is RAG dead? I would be very surprised a local small SOTA embedded model like llama-embed-nemotron-8b doesnt outperform the Haiku layer for this application. Should be pretty cheap and easy to prove out. With 32K context size, you can literally one shot the whole ticket.

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Thu, 23 Apr 2026 12:11:12 +0000

Which quants are you using? I had similar issue until I used Unsloth’s. I would recommend at least UD_6. Also, make sure your context length is above 65K.

https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Thu, 23 Apr 2026 00:53:27 +0000

Q8 or Q6_UD with no KV cache quantization. I swear it matters even more with small activated parameters MOE model despite the minimal KL divergence drop

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 22:04:00 +0000

Llama cpp is vastly superior. There was this huge bug that prevented me from using a model in ollama and it took them four months for a “vendor sync” (what they call it) which was just updating ggml which is the underpinning library used by llama cpp (same org makes both). lmstudio/lms is essentially Ollama but with llama cpp as backend. I recommend trying lmstudio since it’s the lowest friction to start

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 19:23:24 +0000

1. Qwen is mostly coding related through Opencode. I have been thinking about using pi agent and see if that works better for general use case. The usefulness of *claw has been limited for me. Gemma is through the chat interface with lmstudio. I use it for pretty much everything general purpose. Help me correct my grammar, read documents (lmstudio has a built in RAG tool), and vision capabilities (mentioned below, journal pictures to markdown).

2. Lmstudio on my MacBook mainly. You can turn on an OpenAI API compatible endpoint in the settings. Lmstudio also has a headless server called lms. Personally, I find it way better than Ollama since lmstudio uses llama cpp as the backend. With an OpenAI API compatible endpoint, you can use any tool/agent that supports openAI. Lmstudio/lms is Linux compatible too so you can run it on a strix halo desktop and the like.

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 17:24:07 +0000

Ironically, even though I write C/++ for a living, I don’t use it for personal projects so I can’t say how well it works for low level coding. Python works great but there’s a limit on context size (I just don’t have enough RAM, and I do not like quantizing my kv cache). Realistically, I can fit 128K max but I aim for 65K before compacting. With Unsloth’s Opencode templating, I haven’t had any major issues but I haven’t done anything intense with it as of late. But overall, I have not had to stop it from an endless loop which happened often on 3.5.

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 17:16:02 +0000

Inferencing is straight up hard. I’m not accusing them of anything. There’s a crap ton of variables that can go into running a local model. No one runs them at native FP8/FP16 because we cannot afford to. Sometimes llama cpp implementation has a bug (happens all the time). Sometimes the template is wrong. Sometimes the user forgot to expand the context length to above the 4096 default. Sometimes they use quantization that nerfs the model. You get the point. The biggest downside of local LLMs is that it’s hard to get right. It’s such a big problem, Kimi just rolled out a new tool so vendors can be qualified. Even on openrouter, one vendor can be half the “performance” of the other.

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 17:11:19 +0000

1. What do you mean by accuracy? Like the facts and information? If so, I use a Wikipedia/kiwx MCP server. Or do you mean tool call accuracy?

2. 3.6 is noticeably better than 3.5 for agentic uses (I have yet to use the dense model). The downside is that there’s so little personality, you’ll find more entertainment talking to a wall. Anything for creative use like writing or talking, I use Gemma 4. I also use Gemma 4 as a “chat” bot only, no agents. One amazing thing about the Gemma models is the vision capabilities. I was able to pipe in some handwritten notes and it converted into markdown flawlessly. But my handwriting is much better than the typical engineer’s chicken scratch.

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 16:45:26 +0000

Been using Qwen 3.6 35B and Gemma 4 26B on my M4 MBP, and while it’s no Opus, it does 95% of what I need which is already crazy since everything runs fully local.

New comment by syntaxing in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syntaxing — Wed, 22 Apr 2026 16:42:01 +0000

Yes and no. Are you using open router or local? Are the models are good as Opus? No. But 99% of the time, local models are terrible because of user errors. Especially true for MoE, even though the perplexity only drops minimal for Q4 and q4_0 for the KV cache, the models get noticeably worse.

New comment by syntaxing in "SpaceX says it has agreement to acquire Cursor for $60B"

syntaxing — Wed, 22 Apr 2026 00:21:14 +0000

I don’t doubt it is. End of the day, it’s a fine tuned Kimi. They tried to hide it and making their work sound more impressive than it is. It’s easy to have stuff be cheap when you don’t have to train your own model from scratch.

New comment by syntaxing in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

syntaxing — Wed, 22 Apr 2026 00:17:14 +0000

What does heavy RL even mean…similar to how the CEO of cursor said how much better the perplexity got when it’s a terrible metric for model fine tune performance? Let’s be real here, it’s Kimi 2.5 fine tuned for Cursor. There’s nothing wrong with that but they tried to hide it and it’s some work they put in but nothing close to training a model of their own.