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.

1465 results in retrieved candidates

Kimi K2 Thinking: 1T-A32B params, SOTA HLE, BrowseComp, TauBench && Soumith leaves Pytorch

…Agent frameworks, wallets, and managed RAG LangChain Deep Agents for JS: Deep Agents is now in TypeScript/JS (on LangGraph 1.0) with planning tools, sub‑agents, and filesystem access. The team released production‑quality reference tutorials…

AI News · 2025-11-06
AI News—2025-11-06
Sarah Guo

…and test suites provide inexpensive feedback for coding agents, she explained, but passing a test does not establish that a change suits a mature codebase with undocumented dependencies and operational constraints. Her defensibility thesis …

Person · 2026-09-17
Person—2026-09-17
The AI Founder Gene: Being Early, Building Fast, and Believing in Greatness — with Sharif Shameem of Lexica

…things, and learn to train your own models. Plus: The future of Agents and why you should sequence your genome! Latent.Space

Podcast · Latent.Space, Alessio Fanelli · 2023-05-08
PodcastLatent.Space, Alessio Fanelli2023-05-08
Sarah Sachs

…without such a journey reduced the team’s velocity. Custom Agents also required product decisions about capability and control. Sachs identified the difficulty of explaining permissions when an agent’s Slack-channel audience differed from…

Person · 2026-09-17
Person—2026-09-17
Claude Crushes Code - 92% HumanEval and Claude.ai Artifacts

…"dead on arrival". AI Benchmarks and Evaluations Mixture of Agents (MoA): @corbtt introduced MoA model+FT pipeline that beats GPT-4 but is 25x cheaper. Humans prefer MoA outputs vs GPT-4 59% of the time. New SOTA on Arena-Hard (84.8) and…

AI News · 2024-06-21
AI News—2024-06-21
Satya Nadella

…change. Nadella also described building long-running Foundry agents himself. In one example, which he placed in the preceding week, he used Work IQ to build a chief-of-staff agent with persistent memory and then asked it to publish to…

Person · 2026-09-17
Person—2026-09-17
Cursor @ $9b, OpenAI Buys Windsurf @ $3b

…Agent Based Frameworks and Workflows AWS Framework for AI Agents: @LiorOnAI reports that AWS released an open-source framework that lets you orchestrate multiple AI agents and handle complex conversations, able to be deployed locally on…

AI News · 2025-05-05
AI News—2025-05-05
Seek.ai

…rather than requiring users to write SQL. Enterprise data agents and IBM's 2025 announcement By June 2, 2025, IBM described Seek AI as a New York City-based startup building AI agents to harness enterprise data. Sarah Nagy, identified as…

Organization · 2026-09-17
Organization—2026-09-17
Warp CEO Zach Lloyd on why software factories are the next phase of coding

…when AI hit, it turned into a terminal with integrated coding agents. But the competition among CLI tools has dramatically increased in recent years, including from Claude Code, Codex CLI, and Gemini CLI — three products backed by massive…

Article · Richard MacManus · 2026-07-01
ArticleRichard MacManus2026-07-01
Seenia Hong

…NVIDIA on training infrastructure and evaluation for scientific agents, using NeMo and Nemotron. One concrete deployment problem was preserving scientific evidence during document retrieval: figures, tables, formulas and captions can carry …

Person · 2026-09-20
Person—2026-09-20
$200 ChatGPT Pro and o1-full/pro, with vision, without API, and mixed reviews

…discussion about future developments including Multimodal RAG + agents. The 28B parameter size was particularly celebrated for balancing capability with accessibility. PaliGemma 2 Release - a Google Collection (Score: 56, Comments: 7):…

AI News · 2024-12-06
AI News—2024-12-06
Self Pre-Training and Fair Long-Sequence Benchmarks — Part 4 of 4

…of ICLR coverage will focus exclusively on reasoning and agents—the host’s subjective choice for the conference’s biggest topic for AI engineering.

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.