Foobar8568

Well, according to claude and Jevbench, Qwen 3.6 35b with ninfer on a RTX 5090@480W is like 3-5 time slower but 10%-15% better performance on the public set, I could see prefill > 15k for 700-800decode. Latency against what and which hardware? I don't really get jev...

As a non googler, I understood it as "is it webscale" type of jokes.

cheerleader hallucinating agent. That's Gemini.

Because it's a gorgeous piece of history. I have a paper reproduction that is 30m long. Yes, 30meters or I guess like 100 feet? From Citadelles et Mazenot edition, gorgeous books.

You won't have this type of billboard in Paris...And it looks so off.

I yolo vibe develop, but how one end up with 210 files change commits? Unless one shooting a project, there is no way to end up with such scope? I really don't get it.

At work, I am arguing with tech leads that they should sanitize user inputs for a public facing chatbot.

I want to cry.

One thing I would like to know is how fast it is when it's being presented with a 8000 ctx prompt? 16k? 32k?

I have just switched to 5.5. First mistake was stale environment variable, didn't realize it was replaced, "oh my memory had stall data" and that's it. Second one, a powershell command had the wrong syntax. Great for my first two prompts.

Qwen can't train anymore with openai reasoning tokens? I kid I kid.

I am more curious about a 60k prompt... I haven't seen much discussion about large prompts, is it still < 500ms?

Well the Doom demo is again passing a textual structure....I am not really convinced on how it's different than any other llm that execute small context within 100ms. On a MBP M3Max with LFM 2.5B, I get about 500ms -600ms on "source_text": "Invoice #4471 issued March 3, 2026 to Beaver Dam Logistics for $12,840.00, net 30." with a 4 property structure output https://docs.typesafe.ai/primitives/advanced

I can't test it on a better model / my main workstation, but sub 1sec for short prompts is not impressive? I am sure that we can get something like 100ms-300ms with a Qwen 3.8 27b model for a similar query on a 5090 class GPU.

edit: 203ms wall clock on a somewhat busy workstation with https://huggingface.co/LilaRest/gemma-4-31B-it-NVFP4-turbo

I still don't get the point of jev....it's basically an optimized models/runner on really short context and output?

Ninfer is compatible with a nvfp4 model for the 27b. Also nowadays I prefer to use the byteshape one, I get less loops, and I am not sure if I really see a difference in speed or quality. Pure vibe agentic coding on a C++ codebase or ocaml one, ocaml one has codex as reviewer as I am more interested by that project, the other is more for fun.

Considering the ability of men to aim in urinals, Cornucopia is really one of the worst idea.

I wanted so much to play with VR back in the 90s, but most 3d games give me motion sickness. I could barely play 5min of Goldeneye on N64, 2min playing Metroid and I was sick to death (headache, vomiting if I forced myself, feeling sick for hours).

Although I can play many, it's really a hit and miss. And thus I avoided VR not really knowing how it would render me useless.

Also, I think the toe box durability test has a big flaw... At least in my experience with running shoes from Asics (Kayano and the other similar one).

The toe box durability test is just from the top, not both the top and the bottom. My Asics, supposedly among the best in their category, are crapping out after 1 or 2 months of just walking.

And don't forget contract management with the supplier, L1-L2-L3 support, all in one, and integrating as the supplier is useless and your contract is shit.

Oh and you will do also business analysis with the business as claude is too complex for them (read any version of the nocode initiative).

From my experience building different systems, there is no moat anymore ( beside your commercial connections for B2B). If one lack understanding of a domain, he will get it by testing the system. So basically nothing has changed from before AI.

How so?

With weak models, yeah if you get things compiled, with any Opus 4.6 or Codex, not really...

It's a sad parody that people will take as reality.

Lol, and Switzerland has high working hours, but I achieve less in 3 months than 3weeks in Paris.

My US colleagues, like German one,just bullshit on reality of what they produce.

Real problem is more on VC, autonomy and small companies.

Not just legacy dying industry. Whole IT in France and Switzerland runs on consultancy.

Oh and how is it any different than most software engineers?

How many times I heard ORM are bad only to recreate the same shit?

How many times I heard ORM had bad performance and see 1+n stuff everywhere?

How many times I have seen tight coupling in the name of DRY?

Look at the cost of a FP screen replacement, 100 €/chf for the FP4. Mine is going black randomly until I reboot the FP4 one to five times.

I have an FP4, and when it'll die, I will just buy an iphone. Security updates are slow, and after the bullshit of the android upgrade, yeah but no.

AIPocalypse.

> If they keep doing it they'll get a letter from the school and probably a police visit.

It depends of the town/location and region. In our town, police had to be involved several times due to different issues with creeps targeting 12yo or less.

Edit:And I forgot, as it's Switzerland, police moved only because parents were accompanying their kids and almost done justice by themselves. Protecting creeps is a national sport here too.

Where is my Gemma 5?

I post once with a fake/hidden email address to be contacted. I received thousands of DocuSign emails...