virajk_31

Great to see something new..

However I don't understand how are they claiming zero hallucination, how does giving confidence score fix hallucination? or am I missing something here?

I started working similar concept 3 years ago and eventually discontinued the project because of workload.. Great to see someone making the progress :D

Gemini 3.7 benchmarks against GDPVal-AA-V2 were 1525 in Aug blog post. However same model against same benchmark is 1482 in today's blog post of Gemini 3.8 release..

Do they make it intentionally to look previous model less superior than current models? or these are the real numbers when re-ran the benchmark..?

Am not an expert. Putting medium level interactive challenge for first time IPs in X time duration, wouldn't this reduce the bot traffic..

exactly and this applies to only sponsored links which is fair

Reg. goto links, as far as I remember, this has been in place for quite some time. and it only applies to sponsored links. The rest of the links remain unaffected by this..

Your description is misleading a bit, it doesn't save the tokens that are already generated.

I think search is broken..

I bought the Moto signature a month ago , I already assumed it prolly won't support graphene, since some of the previous replies on X indicate that the graphene team requires full hardware compliance with their requirements, and the Signature apparently is not compliant yet.

Anyway I ended up buying a really good smartphone.. just not a graphene supported haha :(

Also this is really great collab from moto & graphene as more vendors will officially recognize Graphene as legit OS (legel/OEM is different concept). I heard month ago Volkswagen banned graphene, hopefully we we will see moving things in opposite direction...

In the context of agents and automation, I believe we’re already NOT HUMANIZING the output. Instead adjusting the prompts so that agents and machines can exchange data in a format that is more suitable for machine-to-machine communication.

OS?? Reallyy, What nonsense is this marketing?

Yes, its because Anthropic took over and wanted to showcase their LLM capabilities by porting such a complex codebas.

Wiping could be the last resort. Instead how about auto creating a new profile! As far as I remember Android profiles isolate apps, files, and system data and providing a fresh environment without erasing the device. To make it feel more authentic there could also be an option to automatically install a few commonly used apps by default. Thats it. (assuming the officials don't have time for an thorough inspection)

Author kept "going" in title because there has been no minor/major release in last two months which unusual for this project if you review the older releases.

Breaking: JavaScript developers create three new frameworks/kits while you were reading this sentence.

Great, I hv been working on similar application for internal use, my approach includes upload pptx - web - download pptx. (Though getting fidelity to upto the mark is really challenging)

Please re-read my comment, I didn't mention anything about Rust. (IK they later switched to Rust. A year ago no LLMs were good at rust, similar to zig today, however its different story now)

Why would Anthropic ever admit this?

No it's vice versa

Anthropic tried hard to port using their LLMs but their models were not trained on enough zig corpus hence failed and they blamed it on Zig's principles

How the turntables lol

Offtopic: I really love the idea of Nostr, BAN is LOCAL. haha!

Submitting any kind of proof will at least reduce the fake reports, though again there is risk of fabrication of the data however those things can be handled at court!

Are the reports listed currently legit or demo data? this is really good though.

this is really good to read, explained in easy language, well done.

It doesn't really matter for One plus/Oppo/Vivo/Realme/IQOO they all share the same parent BBKE, even they share same OS (at least for some variants), and hardware is very identical across the models, its better they if they reduce it to two sub-brands instead this will atleast reduce consumer's confusion and dilemma while making the purchase.

I checked internet speed inside and outside the wasm, and inside wasm its 10x slower, what could be the reason?

I have done something similar for PPTX, keeping the fidility intact was really challenging with computed values & OOXML counterparts and again challanges with different XML implementations like that of MS & Libre..

oh, it is subjective and depends on use cases, for most of my use cases in web dev , it did work really good

web tech - HTML, CSS, JS, and based/derived frameworks