Hacker Newsnew | past | comments | ask | show | jobs | submit | nunodonato's commentslogin

me too! fluxbox and gkrellm for some kick ass desktop "widgets" monitoring the computer :D

I think playwright doesnt capture video, right?

It does. I literally just watched a video of a Playwright test run a few minutes ago.

Yes it does. https://github.com/microsoft/playwright-cli?tab=readme-ov-fi...

I'm pretty sure OP wrote their own version of playwright because they didn't know this existed.


Yeah I’ve never seen it capture video before, but if you specify in your `AGENTS.md` that you want to test certain types of workflows, it will take progressive screenshots using a sleep interval or by interacting with the DOM.

chrome devtools mcp really clutters your context. Playwright-cli (not mcp) is so much more efficient.

Chrome Devtools MCP now has an (experimental) CLI as well and can produce neat things like Lighthouse Audits.

https://github.com/ChromeDevTools/chrome-devtools-mcp/pull/1...

I've only used it a bit, but it's working well so far.


cool! needs to mature a bit, session sharing is a no-go for me as I need to run requests in parallel and it would interfere with each other.

I've been using playwright-cli (not mcp) for this same purpose. It lacks the video feature, I guess. But at least is local and without external dependencies on even more third parties (in your case, vercel). Perhaps you could allow to use a local solution as an alternative as well?

agent-browser runs locally (it’s a Rust CLI + Node daemon on your machine), so there’s no cloud dependency on Vercel, it’s just built by the Vercel Labs team. Everything stays local :)

are you a creative professional? because I see that argument quite often as if people use Adobe CS daily, and then its mostly people who do basic stuff (that photopea or gimp can handle fine), but they like to feel "pro" by launching their pirated version of photoshop.

I use krita, adobe substance 2024, blender and whatever other software. Professionally.

When I hear these arguments I just think these people are simply chained.


Gimp is ass, what takes me 5 minutes in Photoshop needs an hour in GIMP. Also I edit photos occasionally in lightroom. I actually daily Linux, but I still have to dual boot for gaming and Adobe.

Also Linux isn't flawless either, Fedora broke sleep on my full AMD PC since like a month now and no agent could successfully debug it.


you can use 4B for that, its quite good


you can do web searches in lm studio. just connect an mcp that does it. Serpapi has an mcp, for example


Also, I had several experiments where I was interested in just 5 to 10 websites with application specific information so it works nicely for fast dev to spider, keep a local index, then get very low search latency. Obviously this is not a general solution but is nice for some use cases.


woah dude, take it easy. There are no missing features, there are more feature. You might just not be finding them where they were before. Remember this is still 0.x, why would the devs be stuck and not be able to improve the UI just because of past decisions?


the reason he (probably) wants that feature so badly is cos it crashes his amdgpu driver when he tries inferencing lol

although, as an amd user, he should know that both vulkan and rocm backends have equal propensity to crap the bed...


edit: disregard, new version did not respect old version's developer mode setting


Go to settings developer and enable developer mode


[flagged]


I'm really glad I bought Strix Halo. It's a beast of a system, and it runs models that an RTX 6000 Pro costing almost 5x as much can't touch. It's a great addition to my existing Nvidia GPU (4080) which can't even run Qwen3-Next-80B without heavy quantization, let alone 100B+, 200B+, 300B+ models, and unlike GB10, I'm not stuck with ARM cores and the ARM software ecosystem.

To your point though, if the successors to Strix Halo, Serpent Lake (x86 intel CPU + Nvidia iGPU) and Medusa Halo (x86 AMD CPU + AMD iGPU) come in at a similar price point, I'll probably go with Serpent Lake, given the specs are otherwise similar (both are looking at 384-bit unified memory bus to LPDDR6 with 256GB unified memory options). CUDA is better than ROCm, no argument there.

That said, this has nothing to do with the (now resolved) issue I was experiencing with LM Studio not respecting existing Developer Mode settings with this latest update. There are good reasons to want to switch between different back-ends (e.g. debugging whether early model release issues, like those we saw with GLM-4.7-Flash, are specific to Vulkan - some of them were in that specific example). Bugs like that do exist, but I've had even fewer stability issues on Vulkan than I've had on CUDA on my 4080.


im sure the clang compile times are very respectable, but for llms? paltry 200gb/sec compared to the rtx 6000 pros 1.8tb.

sure you can load big(-ish) models on it, but if youre getting <10 tokens per second, that severely limits how useful it is.


With kv caching, most of the MoE models are very usable in claude code. Active params seems to dominate TG speeds, and unlike PP, TG speeds don't decay much even with context length growth.

Even moderately large and capable models like gpt-oss:120b and Qwen3-Next-80B have pretty good TG speeds - think 50+ tok/s TG on gpt-oss:120b.

PP is the main thing that suffers due to memory bandwidth, particularly for very long PP stretches on typical transformers models, per the quadratic attention needs, but like I said, with KV caching, not a big deal.

Additionally, newer architectures like hybrid linear attention (Qwen3-Next) and hybrid mamba (Nemotron) exhibit much less PP degradation over longer contexts, not that I'm doing much long context processing thanks to KV caching.

My 4080 is absolutely several times faster... on the teeny tiny models that fit on it. Could I have done something like a 5090 or dual 3090 setup? Sure. Just keep in mind I spent considerably less on my entire Strix Halo rig (a Beelink GTR 9 Pro, $1980 w/ coupon + pre-order pricing) than a single 5090 ($3k+ for just the card, easily $4k+ for a complete PCIe 5 system), it draws ~110W on Vulkan workloads, and idles below 10W, taking up about as much space as a Gamecube. Comparing it to an $8500 RTX 6000 Pro is a completely nonsensical comparison and was outside of my budget in the first place.

Where I will absolutely give your argument credit: for AI outside of LLMs (think genAI, text2img, text2vid, img2img, img2vid, text2audio, etc), Nvidia just works while Strix Halo just doesn't. For ComfyUI workloads, I'm still strictly using my 4080. Those aren't really very important to me, though.

Also, as a final note, Strix Halo's theoretical MBW is 256 GB/s, I routinely see ~220 GB/s real world, not 200 GB/s. Small difference when comparing to GDDR7 on a 512 bit bus, but point stands.


I have my own telegram bot that helps me and my wife. Reminders, shopping list, calendar. Small and simple, gets the job done :) At the start of the day it greets with a briefing, can also check weather and stuff

Btw, I'm in the process of training my own small model so that I can run it on my cpu-only VPS and stop paying for API costs


The API cost...ughhhhh

I set $10 on fire the other day as I was running through some tests.

Like old school arcade games "Please insert more ${money} to keep playing...". Local, smaller, specialized (unix philosophy?) seems like the way to go so you don't bk yourself having AGI distill pintrest recipes to just recipes.


I've been using GLM 4.7 with Claude Code. best of both worlds. Canceled my Anthropic subscription due to the US politics as well. Already started my "withdrawal" in Jan 2025, Anthropic was one of the few that was left


I'm in the same boat. Sonnet was overkill for me, and GLM is cheap and smart enough to spit out boilerplate and FFMPEG commands whenever it's asked.

$20/month is a bit of an insane ask when the most valuable thing Anthropic makes is the free Claude Code CLI.


I've recently switched to OpenCode and found it to be far better. Plus GML 4.7 is free at the moment, so for now it's a great no-cost setup.


I don't know, I max out my Opus limits regularly. I guess it depends on usage.


> I'm in the same boat. Sonnet was overkill for me, and GLM is cheap and smart enough to spit out boilerplate and FFMPEG commands whenever it's asked.

Do you even need an subscription to any service for that? Is a free tier not enough?


Are you using an API proxy to route GLM into the Claude Code CLI? Or do you mean side-by-side usage? Not sure if custom endpoints are supported natively yet.


This works: $ZAI_ANTHROPIC_BASE_URL=xxx $ZAI_ANTHROPIC_AUTH_TOKEN=xxx

  alias "claude-zai"="ANTHROPIC_BASE_URL=$ZAI_ANTHROPIC_BASE_URL ANTHROPIC_AUTH_TOKEN=$ZAI_ANTHROPIC_AUTH_TOKEN claude"
Then you can run `claude`, hit your limit, exit the session and `claude-zai -c` to continue (with context reset, of course).

Someone gave me that command a while back.


thats pretty much what I do, I have a bash alias to launch either the normal claude code, or the glm one


This is the official guide: https://docs.z.ai/devpack/tool/claude


I much prefer OpenCode these days, give it a try.


I did, I couldnt get used to it and didn't get so good results. I think Claude Code's tools are really top notch, and maybe the system prompt


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: