4 23

FDwork

fdwork

AI & ML interests

None yet

Recent Activity

liked a model 8 days ago

alvarobartt/ghibli-characters-sd3.5-lora

liked a model 8 days ago

calcuis/sd3.5-medium-gguf

liked a model 8 days ago

prompthero/openjourney-v4

View all activity

Organizations

None yet

liked 3 models 8 days ago

liked a model 19 days ago

ibm-granite/granite-4.0-h-tiny

Text Generation • Updated Nov 3, 2025 • 15.6k • 190

reacted to 19arjun89's post with 🚀 19 days ago

Post

3458

Update: Making My AI Recruiting Assistant More Deterministic, Auditable, and Bias-Aware

Hi everyone — I wanted to share a progress update on my AI recruiting assistant and some recent changes focused on reliability and transparency.
The goal of this project is to build a decision-support tool for recruiters that doesn’t just “sound confident,” but can actually explain why it produces a given recommendation.

Link: 19arjun89/AI_Recruiting_Agent

Over the last few iterations, I’ve focused on three areas:

1) Deterministic Verification of Job Requirements (Skills)

Previously, required skills were extracted by an LLM from the job description. While this worked well, it still relied heavily on model behavior.

I’ve now added a verification layer that:

Requires every “required” skill to be backed by a verbatim quote from the job description

This means hallucinated skills are explicitly detected and removed before scoring.

The system now shows:

What the model extracted
What was verified
What was dropped
Why it was dropped

This makes the requirements pipeline auditable instead of opaque.

2) Evidence-Based and Weighted Culture Verification

Culture matching is usually where AI systems become vague or subjective.

I’ve reworked this part so that:

Culture attributes are framed as observable, job-performance-related behaviors (e.g., audit readiness, operational reliability, security rigor)

Each matched attribute must include verbatim resume evidence

Matches are classified as:

Direct evidence (full weight)
Inferred evidence (partial weight)
Scoring is now weighted:
Direct = 1.0
Inferred = 0.5

This prevents “vibe-based” culture scoring and makes the math transparent.

The output now shows:
The weights used
Which attributes were supported directly vs inferred
Which attributes were missing

3) Improved Bias Audit Prompt
I’ve also upgraded the bias audit prompt to be more structured and actionable.

liked a model 22 days ago

unsloth/Falcon-H1R-7B-GGUF

8B • Updated Jan 6 • 3.6k • 19

liked a model 23 days ago

tiiuae/Falcon-H1-1.5B-Deep-Instruct

Text Generation • 2B • Updated Jul 31, 2025 • 555 • 35

liked a model 24 days ago

RuneXX/LTX-2-Workflows

Updated about 18 hours ago • 255

liked a model 28 days ago

unsloth/GLM-4.7-Flash-GGUF

Text Generation • 30B • Updated 11 days ago • 324k • 521

New activity in zai-org/GLM-4.7-Flash 28 days ago

Amazing! look what this local AI generated in 5 minutes.

👀 🤯 4

#36 opened about 1 month ago by

robert1968

liked a model 28 days ago

zai-org/GLM-4.7-Flash

Text Generation • Updated 25 days ago • 1.75M • • 1.56k

reacted to marksverdhei's post with 😎 about 1 month ago

Post

2998

Inspired by the heroes of day zero quants ( @TheBloke @danielhanchen @shimmyshimmer @bartowski ), I decided to join the race by releasing the first FP8 quant of glm-4.7-flash! Not as easy as i expected, but I'm happy i was still able to have it working within a few hours after the original model was released! Interested in feedback if anyone wants to try it out!

marksverdhei/GLM-4.7-Flash-FP8

Note: If my PR to vLLM isn't merged yet you might have to use my fork. Cheers! 🤗