_345

i got half way through the readme for this project and had the same thought and got sad and just left the page

The oneplus open (2023) is such a great phone, what a shame

What inspired you to make this?

i dont understand why you would use this. i think it needs more examples

I feel like its only useful if the work you are doing doesn't have correctness as a high priority. If your work is okay with something only mostly being correct and it can just be slopped together over time then yes throw 500 agents at it. But otherwise you can't really review all that work as a single human and will quickly run out of capacity

This makes so much sense as to why I've always felt that Opus 4.8 was leagues ahead of GPT 5.5. It's so good at taking underspecified requirements and filling in the gaps with sensible approaches for your project

I did the same thing but it's 25 feet hahaha, love to see this

Just you as an adult. It's always been that infantile

any guesses how?

I'm not letting Jenna from HR log into my personal machine with access to all of my lifelong data though. I do let my claude bypass permissions though

Best comment in this thread

In my case no, I actually saw worse performance with fable medium and switched back to opus high and xhigh

way worse things can happen than your machine being bricked, if a malicious actor can weaponize an agent to do their bidding

I moved to Firefox as soon as they began threatening uBlock Origin support and people started switching to Lite, I find it silly that people were tweaking their registries just to stay on a sinking ship for a few more months lol.

... how. how is that even possible. pirated usage plans?

Agree wholeheartedly. I think that Anthropic has just invested more effort in creating a better DevEx than OpenAI, and so people just "feel" that claude code is better but they're about the same really, claude code might be 5% better at best.

It doesn't sound like he was booed, more like the topic of AI was booed when mentioned

yes just ask claude to add quick-silence-dissension to your project

It's a seriously degraded experience from a developer's perspective. Okay you've got one local LLM installed finally after configuring everything perfectly, what happens when you want to run a second instance? Now you've blown past your vram and system ram limits, and you're stuck to just one.

Furthermore, the model they recommend doesn't quite reach ~gpt-5.4-mini level performance- that quality dip means you may as well just pay for something like Kimi K2.6 via openrouter if you want a something ~>= sonnet 4.6 in performance as a backup for when you run out of anthropic/openai usage.

I've been experimenting with Hermes, I'm convinced hermes is also just bad. Like as a harness it has got to be doing something to lobotomize these models- Even GPT-5.4 performs badly in Hermes vs just using it in Codex.

If you're okay with sonnet level performance, this sounds like a straight upgrade. But I find that sonnet messes up too much, that it ends up not being worth cost optimizing down to using it or another sonnet-level model. Glad to have this as an option though

Also why light text on black background?

im really curious how you think this is worse than the other way around

I think I like this article and I haven't finished it yet, but I don't think the bottleneck has shifted to non-human with the advent of agentic AI. It's still the human (deciding what product direction to take, reviewing code, etc)

This is eye opening

this would work better if gemma 4 actually could tell what it was looking at

The page is hard to read on landscape browsers like Chrome on Win11.

We need more voices like this to cut through the bullshit. It's fine that people want to tinker with local models, but there has been this narrative for too long that you can just buy more ram and run some small to medium sized model and be productive that way. You just can't, a 35b will never perform at the level of the same gen 500b+ model. It just won't and you are basically working with GPT-4 (the very first one to launch) tier performance while everyone else is on GPT-5.4. If that's fine for you because you can stay local, cool, but that's the part that no one ever wants to say out loud and it made me think I was just "doing it wrong" for so long on lm studio and ollama.

I actually asked chatgpt to recommend me a great starter tmux conf, and it gave me 80% of this blog post. Not an insult btw.

Weirdly, after submit, the post went up as "VR game I've ever played wasn't a VR game". I had to edit it to add "The best" back in. Misfiring title filter maybe?

That's about a 8:30 mile scaling for the fact that its harder when you have to cover more distance... seems pretty reasonable to me as a fitness baseline for the army. I would struggle to make that now but if I had one month to prep I could clear that