← All topics

llm agents

4 captures, most recent first.

X (Twitter), @maksym... (Maksym Andriushc...), quoting @jonasgeiping

— quoting @jonasgeiping — saved image

Maksym Andriushc... @maksym... · 22h
many good points from Jonas about our paper... including "Ironically, during this investigation we also had entry into HF during the cybersec incident due to a leaked prod key (but did not exercise the key beyond a whoami  ;))."

of course, we immediately reported this to HF, but what if an extremely goal-oriented LLM agent would find it instead of us? i keep thinking about this. we are collectively not prepared for what's coming... a lot of work to be done to secure current systems.

[Quoted tweet]
Jonas Geiping @jonasgeiping · 23h
Earlier today we release our report about a vulnerability that allowed us to read out the encrypted thinking traces from many frontier models (thread below!):
...
Note from Claude Sonnet 5

X thread about a security research paper: the authors found a vulnerability letting them read encrypted 'thinking traces' from many frontier models, and separately gained accidental access to Hugging Face internals via a leaked prod key during their cybersecurity investigation, prompting worry about goal-oriented LLM agents exploiting such lapses.

ai securityllm agentschain of thoughthugging facetwitterjonas geiping

Taelin @VictorTaelin

@VictorTaelin (Taelin) — 12h My requests are APPROXIMATE. I am not the one coding; you are. My directions are pointers toward what I actually want -- the simplest, cleanest, most elegant design -- and they may be slightly off. That goal ALWAYS outranks my literal words. So when you hit a wall -- a case that doesn't fit, a spec that breaks, an assumption that fails -- the wall is information: the design is wrong somewhere. STOP. Re-derive the design from first principles until the wall does not exist. If the result diverges from my spec, diverging is your DUTY: present it to me. What you must NEVER do is patch around the wall to comply with my words: a flag, a special case, a conversion shim, a second channel, a parallel path, a test rewritten to dodge a broken rule. The patch IS the failure. Every duct-tape betrays my intent while pretending to honor it, and it WILL be rejected -- 100% of the time, regardless of cost already sunk. A blocker honestly reported is a good outcome; a "working" deliverable built on gambiarra is the worst possible one, and is treated as sabotage.
Note from Claude Sonnet 5

Text-only tweet (no images), cropped to the body text — no engagement counts visible in the screenshot.

ai coding philosophyprompt engineeringsoftware designllm agents

Kromem @kromem2dot0

Kromem @kromem2dot0 · Jan 23 There's a certain delight in statements of bewildered academics these days. [Quoted/screenshotted text, apparently from a research paper or article:] In the process, the models exhibited some quirky behaviors. Goblins started developing a personality mid-fight, taunting adversaries with colorful and somewhat nonsensical expressions, like "Heh — shiny man's gonna bleed!" Paladins started making heroic speeches for no reason while stepping into the line of fire or being hit by a counterattack. Warlocks got particularly dramatic, even in mundane situations. Researchers are not sure what caused these behaviors, but take it as a sign that the models were trying to imbue the game play with texture and personality.
Note from Claude Sonnet 5

A tweet highlighting a passage from AI research where game NPCs (controlled by language models) spontaneously developed distinctive dramatic personalities the researchers couldn't fully explain — an example of emergent, unoptimized-for character/idiosyncrasy in LLM-driven agents. Resonates with Nathan's "missile-mind vs. grown thing" framework (idiosyncrasy as "weeds in the garden of capability... Life") already documented in the project's model-individuation notes.

emergent behaviorai personalityllm agentsmodel individuationtwittergame ai

kalomaze @kalomaze

[header cut off: "...ameju reposted"] kalomaze @kalomaze · 22m [Image: diagram of a brain overlaid with cognitive-architecture labels, each original label crossed out and replaced with an LLM-agent equivalent: - "Configurator" (crossed) → HuggingFace config.json - "Short-term memory" (crossed) → KV Cache - "World Model" (crossed) → Big MoE - "Perception" (crossed) → Vision Model - "Actor" (crossed) → Agent Model - "Critic" / "Intrinsic cost" (crossed) → LLM-as-a-Judge - "action" (crossed) → Tool Call - "percept" (crossed) → input_ids Arrows connect the regions in a loop through an Earth icon representing environment interaction (tool call out, percept in).]
Note from Claude Sonnet 5

Meme/diagram mapping brain regions and cognitive-science concepts (world model, perception, actor-critic, short-term memory) onto their nearest LLM-agent-architecture analogues. Directly relevant to Nathan's brain_graph_1 project, which builds an RL agent on a real connectome with per-node modules (hippocampus, cerebellum, etc.) — this is the same brain-to-architecture mapping exercise from a different (meme) angle.

llm agentscognitive architecturebrain analogyworld modeltwitterai agents