IceWreck

I have switched to https://chatto.run/. Its actually well engineered (not vbibecoded), the devs are responsive and is kinda opinionated instead of do everything and we cater for every possible scenario but be great at nothing like matrix.

Vitess/Planetscale? Neki is essentially a version of Vitess for Postgres fom the same guys.

Ive been poking with the muse code binary - seems to be written in rust, looks similar to codex but either its a very hard fork (i also see dissimilar things like config format is different, no acp, etc) or is just heavily inspired by it (more likely).

Does this mean I can finally connect to a ducklake instnace hosted remotely? i.e. DuckLake is writing to disk on the remote server and my client is just a client.

Because rn even with Postgres as a catalog my client needs access to the underlying storage to use Ducklake.

> He then open sourced llama and wanted to be the android of llms.

Well the original llama did kick off the era of open source LLMs. Most original open source LLMs were based on the llama architecture. And look where we are now OSS modles are very close to frontier.

It may not have benefitted Meta but it commoditizatised LLMs.

Didn't OpenAI say something similar about GPT-3? Too dangerous to open source and then afew years later tehy were open sourcing gpt-oss because a bunch of oss labs were competing with their top models.

Yep, I understand I was giving an example to the person I was replying to.

> So while feasible it's only great for batch jobs not interactive usage.

I mean yeah true but depends on how big the model is. The example I gave (Qwen 3.5 35BA3B) was fitting a 35B Q4 K_M (say 20 GB in size) model in 12 GB VRAM. With a 4070Ti + high speed 32 GB DDR5 ram you can easily get 700 token/sec prompt processing and 55-60 token/sec generation which is quite fast.

On the other hand if I try to fit a 120B model in 96 GB of DDR5 + the same 12 GB VRAM I get 2-5 token/sec generation.

It does if you use an inference engine where you can offload some of the experts from VRAM to CPU RAM. That means I can fit a 35 billion param MoE in let's say 12 GB VRAM GPU + 16 gigs of memory.

> This is speculative, but I suspect that if we dropped one of the latest, most capable open-weight LLMs, such as GLM-5, into a similar harness, it could likely perform on par with GPT-5.4 in Codex or Claude Opus 4.6 in Claude Code.

People have been doing that for over a year already? GLM officially recommends plugging into Claude Code https://docs.z.ai/devpack/tool/claude and any model can be plugged into Codex CLI (it's open source and can be set via config file).

> What Google and OpenAi have open sourced is their Agents SDK, a toolkit, not the secret sauce of how their flagship agents are wired under the hood

And how is that any different? Claude Code is a harness, similar to open source ones like Codex, Gemini CLI, OpenCode etc. Their prompts were already public because you could connect it to your own LLM gateway and see everything. The code was transpiled javascript which is trivial to read with LLMs anyways.

basedpyright has existed for years and now we have pyrefly from meta too. I think ty is also working on one.

At this point why not make the agents use a restricted subset of python, typescript or lua or something.

Bash has been unchanged for decades but its not a very nice language.

I know pydantic has been experimenting with https://github.com/pydantic/monty (restricted python) and I think Cloudflare and co were experimenting with giving typescript to agents.

I've been using https://github.com/sipeed/picoclaw

Blackberry OS 10 was also running QNX under the hook afaik.

This is exactly what Google did with Windsurf and similar to what Meta did with Scale AI. Seems like a rising trend,

We need nanosecond precision for trading - basically timestamping exchange/own/other events and to measure latency.

You're linking to a different version - this is the one that most people use https://github.com/modernc-org/sqlite

LlamaCPP supports offloading some experts in a MoE model to CPU. The results are very good and even weaker GPUs can run larger models at reasonable speeds.

n-cpu-moe in https://github.com/ggml-org/llama.cpp/blob/master/tools/serv...

I was using aider quite a lot from ~ 7 months ago to ~ 3 months ago. I had to stop because they refuse to implement MCPs and Claude/Codex style agentic workflow just yields better results.

Does it download torrents on your server or web torrent on your browser? - the readme really doesn't say.

Imo downloading on the server is more useful. Web torrent is great but I don't think it's very practical in many places.

Huawei and Honor are seperate app stores?

And Oppo and Vivo too?

In both instances one company owns the other - why have competing app stores?

Why not Linux? The UI looks to be some kind chrome based thingy - probably electron - should be easy to port to Linux.

Also is there a link to the source?

You can already use in it ollama by using the unsloth quants:

``` ollama run hf.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M ```

> And what is the best offline model for coding?

That would depend on your hardware.

Slightly controversial compared to other comments here but I haven't used Grammerly at all since LLMs came out. Even a 4B local LLM is good enough to rephrase all forms of text and fix most grammer mistakes.

I think Allo and YouTube Chat were also around for the same time as Duo.

Anthropic "warned" Claude 4 is so smart that it will try to use the terminal (if using Claude Code) or any other tools available (depending on where you're invoking it from) to contact local authorities if you're doing something very immoral.

According to the readme here - https://huggingface.co/google/gemma-3n-E4B-it-litert-preview

E4B has a score of 44.4 in the Aider polyglot dashboard. Which means its on-par with gemini-2.5-flash (not the latest preview but the version used for the bench on aider's website), gpt4o and gpt4.5.

Thats sounds very good - image what a coding focused version of this could do if this is a "generic" embedded only model.

On the other hand - this does have a much lower score for livecodebench.