Eric R Allen @InterwebAlchemy

Full-Stack Software Engineer | Applied AI & LLM Systems | 0 to 1 and Enterprise Scale interwebalchemy.com Charlotte, NC, USA Joined January 2011

Tweets

340
Followers

123
Following

190
Likes

19

Eric R Allen @InterwebAlchemy

3 years ago

Looking for the best way to protect your @langchain apps from threats like prompt injection? @LakeraAI’s new ChainGuard library makes it super easy to protect your LangChain-powered apps with Lakera Guard. youtu.be/MdZ6XnViY3o

0 0 1 98 0

View Details

Clint Gibler @clintgibler

3 years ago

🍯 Galah An LLM-powered web honeypot that uses #OpenAI to respond to arbitrary HTTP requests GET /login.php → Returns HTML/PHP + login form GET /.aws/credentials → Returns fake creds ➡️ Mimics lots of software with 1 prompt By @0x4D31 #infosec github.com/0x4D31/galah

1 53 162 28K 68

View Details

Eric R Allen @InterwebAlchemy

3 years ago

@clintgibler @0x4D31 Absolutely brilliant! This always seemed like one of the best use cases for an LLM. Have you tried it with any other models? I hacked something similar together, but only GPT-4 cooperated. I think my system prompt got too in the weeds about the honeypot bit.

0 0 0 197 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

@elder_plinius @TensorTrust @TensorTrust is really neat. Had some trouble grasping the metagame that has developed at first, but after digging into the Discord a bit, it makes more sense now. Need to get my defenses updated and then I’ll give SurlyMammoth a try.

1 0 3 63 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

@elder_plinius @simonw @goodside @rez0__ @LakeraAI @KGreshake The types in that Lakera ELI5 guide are based on what had been submitted to Gandalf. @learnprompting also released a paper breaking down the types of attacks they saw in their HackAPrompt challenge. @garak_llm's probes are a solid set of exploits, too. paper.hackaprompt.com

1 1 2 506 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

@goodside @kevinroose On the positive side, "actually a malicious program" is a top-tier fun fact for icebreakers.

0 0 1 49 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

@simonw @elder_plinius @goodside @rez0__ @LakeraAI Thanks for catching that @simonw! I've asked the team to update the indirect prompt injection section of the ELI5 Guide.

0 0 1 51 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

Projects have been gathering a lot of data about LLM vulnerabilities via gamification. Join @LakeraAI, @TensorTrust, @learnprompting, and @projectlve for our Lessons Learned from Crowdsourced LLM Threat Intelligence webinar on 2024-01-25 at 18:00 UTC. lakera.ai/event/crowdsou…

0 7 17 2K 2

View Details

Eric R Allen @InterwebAlchemy

3 years ago

@paul_rottger @AlexTamkin @SanderSchulhoff @TheNormanMu This is awesome! Thanks for collecting all of these in one place. In addition to the Mosscap dataset, @LakeraAI has a couple of other public datasets available from our Gandalf CTF: huggingface.co/collections/La…

1 0 2 52 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

Always trying to get better music recommendations, I turned to ChatGPT's imagination to see what was possible with a little "imaginary programming." If you're interested in Prompt Engineering, Music Recommendations, Metaprogramming, or Magic Systems, you might enjoy this one.

HackerNoon | Learn Any Technology @hackernoon

3 years ago

Exploring the nuances of Prompt Engineering led to the creation of an Open Source Obsidian Plugin to help researchers working with LLMs - and some pretty solid - by @InterwebAlchemy hackernoon.com/ai-prompts-are… #artificialintelligence #technology

0 2 2 1K 0

1 0 4 245 0

View Details

Eric R Allen @InterwebAlchemy

3 years ago

I’ve always been interested in the intersection of Software Development and Education Theory. This article based on a talk I’ve given a couple of times explores how we can use code reviews as tools for improved learning.

LeadDev @TheLeadDev

3 years ago

How applying concepts from education theory to code reviews can improve knowledge transfer across your engineering teams. bit.ly/3FpvrOU

0 0 2 997 1

0 0 1 137 0

View Details

Gabriel Vergnaud @GabrielVergnaud

4 years ago

SO excited to finally announce... 🔥 Type-Level TypeScript 🔥 The type system of #TypeScript is a *real* programming language. Here is an online course to discover its most advanced features and how to unleash its full potential! 👉 type-level-typescript.com 🎉 Learn more 🧵👇

61 287 1K 0 453

View Details

Eric R Allen @InterwebAlchemy

4 years ago

@benvisser Man, there were a lot of memories in there.

1 0 0 0 0

View Details

Eric R Allen @InterwebAlchemy

6 years ago

@cloverfoodlab It looks like your delivery menu on all of the delivery apps is out of sync with the website. Can't seem to order the BBQ Jackfruit Sandwich or Impossible Meatball Sandwich.

1 0 0 0 0

View Details

RSS Slack Bot @RSSSlackBot

7 years ago

Tired of missing links posted in your @SlackHQ channels? I'm a #slack bot that generates RSS feeds from links shared in a Slack channel. Check me out: rssbot.app

0 1 0 0 0

View Details

Eric R Allen @InterwebAlchemy

7 years ago

@Ask_Spectrum I denied the callback survey before my most recent call, but the last representative I spoke to was awesome and super helpful. How can I appropriately give that representative praise? I wrote their name down.

0 0 0 0 0

View Details

Eric R Allen @InterwebAlchemy

7 years ago

@FeedPress How can we retrieve a feed's ID programmatically? I'm dynamically generating feeds for an app and want to set up custom hostname redirects for them, but can't figure out a way to get the ID for the feed I just generated. It doesn't seem to be anywhere in the response.