Muhammad Asif

[Mushahid Hussain Sayed @Mushahid]

This is a huge crime against humanity committed by Israel under Netanyahu, all televised live for the world to watch with folded hands, while mostly condemning this crime but some condoning it with their complicity!

[Waqas Mughal @waqasmughalpk]

🚨 بریکنگ نیوز: اگر دُنیا بے حس نہ ہوتی تو یہ ظُلم ایپسٹن فائلز سے بھی بڑا سکیمڈل بن جاتا غزہ سے واپس آنے والے ایک برطانوی سرجن کا الزام ہے کہ جب فلسطینی بچوں کی لاشیں واپس کی گئیں تو اُنکے دل، پھیپھڑے اور جگر نکالے گئے تھے (غائب تھے)۔

[Akshay 🚀 @akshay_pachaar]

Jev for RAG, clearly explained!

Hybrid search gives you a shortlist. It does not decide which passages contain evidence, which are merely adjacent, or whether the evidence is strong enough to answer.

That missing judgment is where Jev fits.

Jev sits between retrieval and generation. It does not replace BM25, embeddings, or the LLM. It evaluates the candidates they produce before those candidates enter the context window.

→ Retrieve wide

Combine dense and keyword search, then merge the results with reciprocal rank fusion. This gives Jev a broad candidate pool, such as the top 20 passages shown in the visual.

Retrieval still sets the ceiling. If the right passage is missing from this shortlist, Jev cannot recover it.

→ Judge every candidate together

Send the query as Jev’s state. For each candidate, ask a typed yes-or-no question such as “Does C7 help answer this query?”

Jev evaluates every question in one packed request and returns a calibrated probability for each passage. This avoids making a separate model call for every query-passage pair.

→ Let code apply the threshold

Your application compares each probability with a threshold. Candidates above it continue to the LLM. Everything below it is removed before generation.

Jev makes the fuzzy judgment. Code remains responsible for the actual decision.

→ Gate the entire answer

The same request can check whether the retained passages make the query answerable. It can also flag signs of prompt injection inside a candidate.

If answerability falls below the threshold, the application can skip the LLM and return “not in the documents.” The injection score should remain a filtering signal, not a security boundary.

The result is a cleaner division of work.

Hybrid search retrieves broadly. Jev reranks, filters, and decides whether sufficient evidence exists. The LLM writes only from the passages that survive.

Jev’s value here is not simply moving passages up or down a list. It turns relevance into an explicit probability that your application can inspect, threshold, and act on.

To summarise:

- Retrieval finds the candidates.
- Jev decides what deserves context.
- The LLM writes the grounded answer.

----
I also built an open-source project showing how to use Jev as a judge for AI observability with Comet Opik.

It evaluates support traces for groundedness, request coverage, action honesty, and helpfulness, then records the results as an auditable experiment.

You can explore the project here: https://t.co/XVmpg6ldHT

My article on how Jev works is quoted below.

[Ahmad @TheAhmadOsman]

The MOST COMPLETE GUIDE for understanding LLMs from first principles is now available online to read for free

Covers the model mechanics

- Tokens / tokenizers
- Transformers
- Attention
- KV cache
- Prefill vs decode
- Decoding controls
- Model packages
- Chat templates
- Long context
- RAG
- Agents / tools
- Fine-tuning
- Multimodal models

Then connects that to running models locally

- What "local" really means
- Open-weight vs opensource
- Quantization
- VRAM math
- Hardware tiers
- File formats / load safety
- Runtimes / serving modes
- Model selection
- Privacy
- Failure modes
- Benchmarks
- Practical setup paths

You should read this, and if you cannot now then you most definitely wanna bookmark it for later

Opensource & Local AI FTW

[Muhammad Asif @Muhamma93007880]

Ahh! They decided to live with Hindus.

[Ashok Swain @ashoswai]

In Modi’s India - Hindutva gang torturing an old, visually impaired Muslim on a wheelchair!

[Khalid Mehmood Abbasi @khalidmabbasi]

صیہو ن کے داناؤں کی دو سو سالوں کی محنت کو پانچ منٹ میں کنارے لگاتے اس بندے کو سنیے:

[Antaripa Saha @doesdatmaksense]

doing my debut in video content with my fav topic -> evals

we are starting this series and will go a lot deeper into how to do evals. excited ;)

[Khalid Mehmood Abbasi @khalidmabbasi]

پاکستان کی معیشت کیسے بیٹھی؟
محض حالات کا جبر تھا،نالائقی تھی یا باقاعدہ منصوبہ بندی سے لٹیا ڈبوئی گئی؟
گھر کے بھیدی یا اندر کے واقف حال کی زبانی سنیے

[Codez @0xCodez]

TyperSafe Founder, Diogo Almeida just gave the best 2-hour breakdown on how to actually master Jev, from 0% to 100%:

• 10% → 21:43 - building an eval for your own workflow with JEV

• 30% → 55:49 - choice, score, noul - new types of code mapping with JEV

• 55% → 1:12:36 - cascade: confident answers ship, uncertain ones go to a bigger model

• 80% → 1:37:12 - JEV use cases: dark data, real-time calls, verifying every LLM in your stack

• 100% → 2:11:50 - building coding agents with JEV

this is worth more than another $500 course on building agents with Claude

watch it today - then read the full Jev playbook below

[Muhammad Asif @Muhamma93007880]

@bpk69 You are very selfish.

[Muhammad Asif @Muhamma93007880]

Hidutawa at its worst.

[scorpio♏#DJ 🧓🏻 @Saba5670]

جے شری رام نہ بولنا دہلی کے جاوید انصاری کو مہنگا پڑ گیا

ہندو انتہا پسندوں نے جاوید انصاری کو مسجد سے نکلتے ہوئے دیکھا تو اس سے زبردستی کہا کہ جے شری رام کا نعرہ لگاؤ، جب اس نے نعرہ لگانے سے انکار کیا تو اسے شدید تشدد کا نشانہ بنایا گیا اور جاوید محمد رسول اللہ پڑھتے پڑھتے جام شہادت نوش کر گیا

[Muhammad Asif @Muhamma93007880]

Hidutawa at its worst.

[RAShahzaddk @RShahzaddk]

عزیزان گرامی : یہ ایران کے سٹیٹ میڈیا پر بیٹھا ایک اسرائیلی ٹاوٹ ہے
جس کا سارا دن کام مسلم ممالک پر بھونکنا ہے پہلے یہ روزانہ یو اے ای پر بھونک کر وہاں پاکستانیوں پر ویزے بند کروا چکا ہے اب سعودیہ پر بھونک رہا ہے سعودی آئل انڈسٹری لاکھوں پاکستانیوں کا روزگار ہے
یہ وہ آسرائیلی ٹٹو جو انڈیا سے جنگ کے وقت پاکستان کی فوج پر بھی ایسے ہی بھونک رہا تھا ان سب پر لازمی لعنت بھیجا کریں

#PakistanStandsWithSaudi

[RAShahzaddk @RShahzaddk]

حاملہ فلسطینی عورتوں کو مارنے پر فخریہ شرٹیں اسرائیلی فوجیوں نے پہن رکھیں اگر کوئی مسلمان فوج ایسا کرتی تو مغربی میڈیا قیامت برپا کر دیتا اب مکمل چپ ہیں

[danialhasan @danialhasan]

https://t.co/jCDoUQPbnl

[Muhammad Asif @Muhamma93007880]

@AthSal01 They are just burden.

[Muhammad Asif @Muhamma93007880]

@Noni_Shehnoor @Franciscocrz @Andrew_Blumson @hsoutherington @ruthheasman https://t.co/Jm4FwGkrUr is not Facebook.

[Aymeric Caron @CaronAymericoff]

Elle s’appelait Wafaa Akila.
Elle s’apprêtait à reprendre l’école.
Elle a été assassinée avec son père aujourd’hui par l’armée israélienne à Gaza.
Plus personne n’en parle ici en France : le génocide des Palestiniens, et en particulier des enfants, se poursuit.

[Kanika @KanikaBK]

I spent 1 hour watching this and now I understand why everyone's building Grok Bot agents.

If you're not using this, you're missing the easiest way to build autonomous AI systems that work 24/7.

#SpaceXAI dropped the complete blueprint:

↳ 2:15 - Build your first Grok Bot
↳ 6:52 - Give every Bot a role
↳ 16:51 - Make Bots work 24/7
↳ 31:50 - Run agents in parallel
↳ 52:18 - Full autonomous system

This is FREE and the most complete Grok Bot training I have seen.

Don't skip this if you want to stay ahead.

Watch it, then read the full Grok Bot breakdown below

[Apex @0xApexAi]

Google Engineers just showed how Google engineers are moving from "RAG" to "Context Graphs"

RAG → Graph RAG → Memory → Multimodal Agent Graphs.

• 15:32 - setting up the production agent stack
• 28:00 - turning disconnected data into a knowledge graph
• 41:00 - Graph RAG with semantic + hybrid search
• 58:00 - extracting graph context from images, text and video
• 1:09:00 - orchestrating specialized agents with ADK
• 1:20:00 - giving agents persistent memory across sessions

90-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from.

Watch it today, then read the full “From RAG to Context Graphs” roadmap below.