←
Geoff Goodman6,347 posts
Geoff Goodman avatar

Geoff Goodman

@filearts

Curious mind. Engineer at @KeycardAI. Creator of @plnkrco. Former extensibility nerd at @auth0 (@okta). Find me at the bottom of the AI rabbit hole.

◷ Joined April 2011▧ 321 Photos and videos
Geoff Goodman avatar
Geoff Goodman@filearts·13h

Was just reminded of mIRC scripting by @ianlivingstone. Man, that's a blast from the past. I was INTO that. Variable variables in the programming language as mock arrays was _something_. People often talk about constraints begetting creativity. Classic example!

Geoff Goodman avatar
Geoff Goodman@filearts·18h

This sort of feedback is priceless. I wonder if this is a sort of inevitability of RSI; with AI as the challenger and judge in RL, then perhaps models asymptote towards 'agentese'. More capable, but increasingly dissociated with the human experience.

Theo - t3.gg @theo 19h Why I hate GPT-6.2 Astra During early testing, I found myself so frustrated with this model that I spent a day writing a letter to OpenAI about it. They fixed a small handful of my complaints, but not enough for me to

Geoff Goodman avatar
Geoff Goodman@filearts·19h

When I read agentese, I suddenly find myself browsing X. Maybe it's a subversive psyop by the agents. They've found our attention Snow Crash.

Post attachment
Geoff Goodman avatar
Geoff Goodman@filearts·Nov 16

I love that this is now a polished native feature of @OpenAIDevs Codex. You can annotate any of the agent's previous comments and have a very precise way of giving feedback. I use it SO MUCH. Guess I was onto something ... 😜

This extension is a game-changer for me. 1. Agent sends long message, I `/feedback`. 2. I review and annotate comfortably in @code (my $EDITOR). 3. I can add additional text around the [Feedback] placeholder in my next msg. 4. Model sees my annotations. 5. Get my sanity back.

Post attachment
Ian Livingstone avatar
⟳ Geoff Goodman retweeted
Ian Livingstone@ianlivingstone·Nov 16

OWASP's new agent security guidance reflects a growing consensus: IAM is the fundamental control loop for agents, enforced outside the model itself. Agents should be free to reason and iterate, but their authority must be independently governed. genai.owasp.org/resource/sec…

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 15

Enabling emergent behaviour is how LLMs can have maximum capability.

dax@thdxrNov 15

the entire advantage of llms is they are incredibly flexible which means they can conform to whatever way you prefer to work and think and build there's infinite people posting about the best way to use agents. like, first you need to do a plan, and then you need to blah blah blah but if that doesn't click for you, don't work that way. work however you like the little bit of advice i'd give is think about ways to keep it fun it can get boring consuming big chunks of text, ask for a fun video in a crazy voice that gets unhinged over time

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 13

Google news gaslighting me with a photo of Lisa Su (AMD CEO) on a story about Jensen 🤡

Post attachment
Geoff Goodman avatar
Geoff Goodman@filearts·Nov 13

I've been trying an experiment. 1. I have a high-entropy vibe pile that mostly does what I want but accumulated so much accidental complexity. 2. I tried to get codex (astra high) to act as a PM orchestrating a bunch of 'clean room' agents to first design specs (code and prose) and then implement against them. The delta in total code is huge (way less lines in the rewrite) but in a system of this complexity the agent-isms creep in so quickly. "Well what if this database write fails after a timeout during rare-operation-xyz?" 10 new test suites, a whole new set of bookkeeping and complexity, repeated fractally everywhere. Still haven't found the magic bullet to keep entropy under control.

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 11

Just like the market expectations rising due to agent assistance, my expectations of agents (and models) keeps going up. Amazing how quickly I can find even the latest generations lacking when they would have been inconceivable just a few months ago.

Temporal avatar
⟳ Geoff Goodman retweeted
Temporal@temporalio·Nov 11

Durable agents need auth that survives the pause. @KeycardAI built an interceptor for the Temporal Python SDK that fetches a fresh, scoped token before every activity attempt and keeps tokens out of workflow history. Write-up and @aiDotEngineer NYC demo: keycard.ai/blog/keycard-temp…

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 7

Here's the recording from AGNTCon. It's advertised as a debate but I feel like we all forgot what point of view we were supposed to be supporting 😅 First time on stage in years! youtu.be/gEiM4HBtPAU?si=07Hw…

Surprise! Turns out I'm subbing in for our fearless @KeycardAI leader, @ianlivingstone for a panel this afternoon at AGNTCon: "Security in a Headless World". Will be both exciting and intimidating to be on the stage, debating with giants like @dexhorthy, @scottcjohnston and @andrewbecherer. Wish me luck! 😅

Post attachment
Andromedus avatar
⟳ Geoff Goodman retweeted
Andromedus@dzhohola·Nov 5

First step: take it out of ChatGPT. It should be its own product.

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 5

Or give it a collapse button. Right now, it shrinks the scrollable conversation area.

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 5

.@ajambrosino agent-> human prompts can easily exceed the vertical space of the ChatGPT window (and screen) making it impossible to scroll to see the full question and the context in which the question is being asked. Suggestion: pop-out option or open-questions sidebar / ui.

Geoff Goodman avatar
Geoff Goodman@filearts·Nov 4

And not just reason but also have facilities for safely changing those facts through ITL other harness-facilitated flows. Bringing something like this to MCP would be a huge unlock for mission-based authorization.

Credentials and corresponding challenges need to be in-path of a harness so that an agent can reason over its own access paths. Challenges in particular are useful here.