Foobar8568

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...

Take a look at the most viewed videos... It's gross.

Basically 90% are just crap done by computers (pre AI), targeting preschoolers.

Memory used : 38GB, and I haven't even started a LLM nor podman, I always fight with memory when using LLM on my mac with 48gb.

And I don't remember to have been able to have pushed to 200k context Qwen 3.6. 3.8 is running on my RTX 5090.

I know companies that are using github, even using public repo, and request their teams to not use SOTA models, but are ok with local models. Just stupid policy.

Well... Everything new is old "A vector space model for automatic indexing" 1975 - https://dl.acm.org/doi/10.1145/361219.361220

Companies are avoid risks, and at this stage, sometimes, I feel that all cloud providers are just buying RAM that they would have bought anyway. Now it's ensure that no company will be willing to pay x digits just for cards. One of my clients is stuck in "we are doing things on premise but we are too cheap to spend a few 100k in cards but we don't want to go on clouds.

7) can't use reranker with it, asked by people for one year or two... 8) ...

I could stand Opus 4.6-4.8, I was impressed by the initial fable model. Codex 5.6 sol xhigh feels like the initial release of fable. Qwen 3.8 27b feels like using haiku or sonnet (I quickly stopped trying them).

I had $310 in (free) credit that I used on fable, and I still had a part of the $200 subscription at that time. You know, subscriptions don't end the moment you click on cancel.

Opus 5 in xhigh can't do basic math as well. They dumbed it down to a point where I just cancelled my subscription yesterday. I used to be a $200 subscriber, dropped to $20 after the fable shenanigans, and use it only when I have no usage left with Codex.

/on The prose is load-bearing unbearable — every sentence feels like it was engineered to sound profound rather than to be read.

Or that people don't cheat at work. Or that everyone write excellent code. Or all the code is secured.

I bought a prebuilt with a 5090 a little over than one month ago, whole system was on sales.

The cost of the prebuilt is now lower than today 5090 price.

Looks like slope benchmarks and results, and as usually, people are mixing MTP numbers with non MTP numbers. Or just 100 token input benchmarks. Or just failed ones as actual measures.

https://github.com/Neroued/ninfer/blob/master/docs/performan...

Category MTP3 stochastic sampler DFlash stochastic sampler DFlash greedy Code 1/15 natural stops; 0/15 prompt-complete 2/15 natural stops; 0/15 prompt-complete 0/15 natural stops Story 9/15 natural stops; the nine Chinese outputs pass requested division and minimum length 8/15 natural stops; the eight Chinese outputs pass requested division and minimum length 10/15 natural stops; five Chinese dialogue outputs are under length Translation 15/15 natural stops; 15/15 pass structural checks 15/15 natural stops; 15/15 pass structural checks 15/15 natural stops; 15/15 pass structural checks Structured 0/15 satisfy the requested complete record/script contract 0/15 satisfy the requested complete record/script contract 0/15 satisfy the requested complete record/script contract

And on my "own" "quick" benchmark, it's slower than vllm.