Search Latent Space

Results for “agents”

Articles, conversations, profiles, and grounded writeups.

?
Search tips

Keyword matches words; semantic matches meaning and exact titles or names; hybrid combines both. In keyword mode, use quotation marks for exact phrases. Author matches published credits. Year applies to posts; wiki entries have no author or publication year. You can also use author:"Ada" or type:podcast in non-regex searches.

Reset filters

Select Apply filters to update results.

164 results in retrieved candidates · Filters applied

Summer 2023: From Model Releases to Working AI Systems

…dependable across updates. Interest in AutoGPT and autonomous agents remains strong, but one participant sees a central product problem: narrowing general-purpose ambition into useful scope. Evaluation tools are emerging to monitor prompt…

Writeup · Date unavailable
Writeup——
Taste Is Your Moat: Figma’s Case for Design After Code Generation

…tool connection used here to pass Figma information to coding agents, so an implementation can reuse the team’s existing components. Setup is acknowledged to be cumbersome; easier setup and broader access are described as ongoing work,…

Writeup · Date unavailable
Writeup——
Teaching Genie the work behind the patch

…than accessing external information. Cosine’s criticism of agents built by wrapping foundation models in tools did not mean those tools were unimportant. Genie had a URL-reading tool, used Perplexity’s API to ask questions and had…

Writeup · Date unavailable
Writeup——
Teaching Robots More Cheaply—and Automating RL’s Hidden Labor — Part 6 of 6

…step is to scale the architecture toward more generalizable agents, including robots that perform tasks from language instructions. Chelsea Finn begins with early robot policies—models that choose motor actions from observations—with just…

Writeup · Date unavailable
Writeup——
The Agent Harness: From Autonomous Loops to Human Attention

…support. Multi-agent orchestration—the coordination of several agents—tool selection and memory are possible next targets for learned behavior. As more of this coordination moves into model weights, the harness may need less scaffolding to …

Writeup · Date unavailable
Writeup——
The Agent Lab Playbook: Build at the Frontier, Specialize Around the Work

…which applications much faster generation will make possible. Agents are not necessarily rational infrastructure buyers. A participant argues that they are vulnerable to prompt injection and tend to reinforce products already prominent in…

Writeup · Date unavailable
Writeup——
The Agent Reasoning Interface: From Shared Documents to Delegated Work

…treats this as an intuition, not a formal definition of agents. As with human colleagues, collaboration reveals working styles, communication habits, and implicit preferences. Consistent performance builds the trust needed to delegate more.…

Writeup · Date unavailable
Writeup——
The AI Coding Factory: From Code Completion to Delegated Engineering

…paths. By the interview, the team described more open-ended agents guided by planning, decisions, and feedback from their environment. That broader autonomy did not imply replacing a whole person. The founders expected the outer…

Writeup · Date unavailable
Writeup——
The Four AI Wars: From Frontier Models to Deployable Systems — Part 1 of 3

…Should it fund foundation models, data centers, GPUs or agents? Alessio opens with this allocation problem. In Singapore, senior financial executives had asked him about state-space models and alternatives to Transformers. He sees technical…

Writeup · Date unavailable
Writeup——
The GPU Is Only as Useful as the System Feeding It

…a demonstrated result against a defined benchmark. Tool use and agents are suggested as further opportunities, with the speaker disclaiming expertise in agents. A nonpublic document attributed to Noam Shazeer introduces the importance of…

Writeup · Date unavailable
Writeup——
The Self-Driving Lab: Turning Alloy Predictions into Experimental Knowledge

…The more immediate request is for vendors to build tools for agents and robots, allowing scientists to operate integrated research systems rather than each instrument separately. The career advice is to bring your specialization into…

Writeup · Date unavailable
Writeup——
The Ultimate Guide to Prompting: From Examples to Engineered Systems

…to delete email is a straightforward mitigation, but useful agents need capabilities that carry consequences. The planned competition aims to test those practical boundaries, including the risk of agents escaping their sandboxes, using…

Writeup · Date unavailable
Writeup——
Your place in Latent Space

Join Latent Space.

Sign in with Google, or get the newsletter by email.

Loading Google sign-in…

or subscribe by email

Free. Change your preferences or unsubscribe any time.