RESK - DEV Community

RESK

Oct 24

Token-Level Filtering Costs 0.15 to 0.34 ms per Token on CPU

#llm #performance #opensource #python

2 min read

RESK

Oct 24

LLM Access Controls and Monitoring: Best Practices for AI Agent Security

#security #ai #llm #accesscontrol

3 min read

RESK

Oct 24

How LLM Evaluation Produces Comparable Numbers: Inside the LFORLA RL Game Agents Benchmark

#llm #evaluation #benchmark #reinforcementlearnin

4 min read

RESK

Oct 23

LLM access controls and monitoring: where the control belongs in the request path

#security #ai #llm #architecture

3 min read

RESK

Oct 23

How to Protect a Patient Booking Chatbot Like Doctolib from Prompt Injection Hidden in Patient Messages

#security #llm #python #tutorial

4 min read

RESK

Oct 22

LLM access controls and monitoring: an implementation guide for AI agents

#security #ai #llm #architecture

1

3 min read

RESK

Oct 22

How LLM Evaluation Produces Comparable Numbers: Inside the LFORLA Satellite Geo QCM Benchmark

#llm #evaluation #benchmark #geo

4 min read

RESK

Oct 21

Protect Conversation Summarization from Memory Poisoning: A TypeScript Tutorial for a Service Like BlaBlaCar

#security #typescript #llm #tutorial

4 min read

RESK

Oct 20

AI Agent Evaluation End to End: How LFORLA Scores a LEGO Build From Brief to Render

#ai #benchmarking #agents #evaluation

5 min read

RESK

Oct 19

LLM access controls and monitoring: the attack path you are probably not logging

#security #ai #llm #devops

4 min read

RESK

Oct 19

How to Protect an LLM-Backed Banking Support Bot from Prompt Leakage and Data Exposure (a service like Qonto)

#security #llm #tutorial #opensource

5 min read

RESK

Oct 18

LLM access controls and monitoring: where the control belongs in the request path

#security #ai #architecture #devops

3 min read

RESK

Oct 18

How an LLM Evaluation Benchmark Produces Comparable Numbers: Inside the LFORLA Mechanism

#llm #evaluation #benchmark #ai

4 min read

RESK

Oct 17

Best practices for implementing LLM access controls and monitoring

#security #llm #ai #architecture

3 min read

RESK

Oct 17

How to Protect a Travel Planning Assistant Like SNCF Connect from Indirect Injection via Scraped Web Pages

#security #llm #tutorial #fastapi

4 min read

RESK

Oct 16

LLM access controls and monitoring: where the check belongs in the request path

#security #ai #architecture #devops

4 min read

RESK

Oct 16

AI Bias Detection: How a Fairness Audit Actually Works

#ai #fairness #benchmark #llm

3 min read

RESK

Oct 15

Best practices for implementing LLM access controls and monitoring

#security #ai #llm #devops

3 min read

RESK

Oct 15

How to Protect a Customer-Support Assistant Like Cdiscount from PII Exfiltration

#ai #security #observability #python

5 min read

RESK

Oct 14

LLM access controls and monitoring: why the permission check happens too late

#security #ai #llm #devops

3 min read

RESK

Oct 14

AI Agent Evaluation: How the LFORLA JS 3D Builder Leaderboard Actually Scores Models

#ai #benchmark #threejs #evaluation

4 min read

RESK

Oct 13

How I Would Protect Automated Listing Moderation at a Service Like Leboncoin Against Crafted Jailbreaks

#security #llm #python #ai

4 min read

RESK

Oct 12

Best practices for implementing LLM access controls and monitoring

#security #ai #devops #programming

3 min read

RESK

Oct 12

LLM Evaluation Explained: How a Benchmark Produces Comparable Numbers

#llm #evaluation #benchmark #ai

3 min read

RESK

Oct 11

Where LLM access controls belong in the agent request path

#security #ai #devops #architecture

3 min read

RESK

Oct 11

How to Protect a Patient Booking Chatbot Like Doctolib Against Prompt Injection

#security #python #llm #tutorial

4 min read

RESK

Oct 10

Best practices for implementing LLM access controls and monitoring

#security #ai #llm #devops

3 min read

RESK

Oct 10

How LLM Evaluation Actually Works: Inside a Benchmark That Produces Comparable Numbers

#llm #evaluation #benchmark #ai

4 min read

RESK

Oct 9

LLM access controls and monitoring: where the check actually belongs

#security #ai #llm #devops

5 min read

RESK

Oct 8

Best practices for implementing LLM access controls and monitoring

#security #ai #llm #devops

4 min read

RESK

Oct 8

Enterprise AI Security at the Logits Level: How resk-logits Blocks Dangerous Tokens Before Sampling

#ai #security #llm #python

4 min read

RESK

Oct 7

Best practices for implementing LLM access controls and monitoring

#security #ai #llm #devops

3 min read

RESK

Oct 7

LLM Evaluation: How a Benchmark Turns Raw Answers Into Comparable Numbers

#llm #evaluation #benchmark #ai

4 min read

RESK

Oct 6

Best practices for implementing LLM access controls and monitoring

#security #ai #llm #devops

1

3 min read

RESK

Oct 5

Where LLM Access Controls Belong in the Request Path

#security #ai #devops #architecture

4 min read

RESK

Oct 5

AI Bias Detection: HY3 vs Nemotron 3 Ultra on the Bias Stereotypes Benchmark

#ai #bias #fairness #benchmark

1

3 min read

RESK

Oct 3

How to Protect a Customer-Support Assistant Like Cdiscount's From PII Exfiltration

#security #llm #tutorial #devops

1

4 min read

RESK

Oct 2

How LLM Evaluation Produces Comparable Numbers: Inside the LFORLA Reverse Engineering Benchmark

#llm #evaluation #benchmark #reverseengineering

2

1

4 min read

RESK

Oct 1

LLM Access Controls and Monitoring: Why the Attack Path Runs Through Over-Scoped Credentials

#security #ai #devops #api

3 min read

RESK

Oct 1

How to Protect Automated Listing Moderation at a Service Like Leboncoin Against Crafted Jailbreaks

#ai #security #observability #python

5 min read

RESK

Sep 30

Election Forecasting Benchmarks: How LFORLA Scores Political Bias in LLMs

#llm #benchmark #politics #evaluation

1

4 min read

RESK

Sep 29

How to Protect a Patient Booking Chatbot Like Doctolib From Hidden Prompt Injection

#security #llm #python #ai

1

4 min read

RESK

Sep 28

AI Agent Evaluation End to End: How the LFORLA Drone Build Benchmark Scores Planning, Sourcing, and Assembly

#ai #benchmark #agents #evaluation

2

3

4 min read

RESK

Sep 27

Protecting Conversation Summarization at a Service Like BlaBlaCar: Stopping Memory Poisoning in Long Threads with resk-llm

#security #llm #python #tutorial

4 min read

RESK

Sep 26

A web page wrote a system prompt. The model obeyed it. (CVE-2026-61732)

#ai #security #llm #opensource

1 min read

RESK

Sep 26

Election Forecasting Benchmarks: How LFORLA Scores Models on 2027 France and 2026 US Predictions

#electionforecasting #benchmarking #llm #evaluation

4 min read

RESK

Sep 25

Before / After: Hardening the Three Layers of an LLM App

#llm #security #python #ai

2 min read

RESK

Sep 24

Prompt Leaking: How Pattern Detectors Stop System-Prompt Leaks Before the Model Sees Them

#security #python #llm #fastapi

4 min read

RESK

Sep 24

How LLM Evaluation Actually Works: Inside the RL Game Agents Benchmark

#llm #evaluation #benchmark #reinforcementlearnin

3 min read

RESK

Sep 24

LLM Evaluation: How a Benchmark Produces Comparable Numbers

#llm #evaluation #benchmark #reinforcementlearnin

4 min read

RESK

Sep 23

Prompt Injection Defense That Turns AI Scanners Into Informants

#security #ai #webdev #opensource

4 min read

RESK

Sep 22

How LLM Evaluation Actually Works: Inside the Satellite Geo QCM Leaderboard

#llm #evaluation #benchmark #vision

1

4 min read

RESK

Sep 21

AI Security for Enterprise: How Agent Observability Captures Every Action with Confidence and Parameters

#ai #security #observability #python

3 min read

RESK

Sep 20

How AI Bias Detection Actually Works: Inside a Fairness Audit That Scores Symmetry, Not Vibes

#ai #fairness #llm #evaluation

1

4 min read

RESK

Sep 20

Best Practices for Implementing LLM Access Controls and Monitoring: The Permission Bitmask Mechanism

#llm #security #ai #python

1

4 min read

RESK

Sep 12

Election Forecasting: How LFORLA Benchmarks Models Before the Vote

#electionforecasting #ai #llm #lforla

1

3 min read

RESK

Sep 12

LLM Access Controls and Monitoring: Best Practices with a Bitmask Firewall

#llm #security #ai #python

1

4 min read

RESK

Sep 12

Stop LLM Jailbreaks at the Logits Level: reskSecure Bitmask Firewall

#llm #security #python #aiagents

4 min read

RESK

Sep 12

Election Prediction Benchmarks: Which AI Model Forecasts Best?

#ai #machinelearning #forecasting #benchmark

1

3 min read

RESK

Sep 9

Stop Prompt Injection in TypeScript: A Zero-Dependency Security Pipeline

#typescript #llm #security #bunjs

1

3 min read

One Year Club