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

The Evolution of the Agent Harness

Sometime around Christmas 2025, AI engineers noticed a change in agents. They started to work! It’s hard to pin down exactly why. Maybe we finally had holiday downtime to try the newest agents with the newest models. Maybe the models had…

Article · Dan McAteer · 2026-08-22
ArticleDan McAteer2026-08-22
Cursor reaches >1000 tok/s finetuning Llama3-70b for fast file editing

…AI Startups, Products and Courses AI-Powered Search and Agents: @perplexity_ai added advisors to guide search, mobile, and distribution efforts. @cursor_ai trained a 70B model achieving over 1000 tokens/s. Educational Initiatives: @svpino…

AI News · 2024-05-17
AI News—2024-05-17
Context Drought

…a daily summary. Memory is becoming the differentiator for agents: The most technically interesting agent thread was around persistent memory and self-improvement. @dair_ai highlighted IBM work on extracting reusable…

AI News · 2026-03-14
AI News—2026-03-14
nothing much happened today

…AI will be the default, software will generate itself, and agents will be the new apps. Open Source Developments: @far__el hinted at upcoming developments in open-source AI models, suggesting potential competition with proprietary models.…

AI News · 2024-09-18
AI News—2024-09-18
not much happened today

…no extra video training data, and no added inference cost. Agents, Local-First Tooling, and Production OrchestrationAgent builders are shifting from demos to production primitives: Mistral launched Workflows in public preview as an…

AI News · 2026-04-29
AI News—2026-04-29
Claude 3 just destroyed GPT 4 (see for yourself)

…of AI models like Claude 3 and OpenAI's offerings. Custom Agents and Optimal Code Generation: Questions arose about whether custom agents could integrate CSV files into their knowledge bases, prompting a technical discussion on file types. …

AI News · 2024-03-04
AI News—2024-03-04
The website of the future may assemble itself for every visitor

…structured content (like WebMCP), generative UI, personal agents, and more. Not to mention trying to find ways to bring users in from third-party AI platforms. “I think it’s a combination of all these crazy different ways,” Sanchez said.…

Article · Richard MacManus · 2026-07-02
ArticleRichard MacManus2026-07-02
There's Ilya!

…was mentioned as a relevant benchmark for evaluating AI agents, although it does not hold the same level of mindshare as MMLU (Multitask Model Language Understanding). Factory.ai published a technical report revealing their Code Droid's new…

AI News · 2024-06-20
AI News—2024-06-20
SpaceXAI Grok 4.6 and Grok @Bot

One of our top recurring themes of the year has been coding agents breaking containment into knowledge work, and it’s clear that the AI teammate/multiplayer/multiagent space is the next big AI battleground. With Claude Tag launching to…

AI News · 2026-08-13
AI News—2026-08-13
ALL of AI Engineering in One Place

…multimodality, evals/ops, open models, code generation, GPUs, agents, AI in Fortune 500, and AI leadership, plus 50+ workshops and expo sessions. Additionally, Anthropic shared interpretability research on Claude 3 Sonnet, revealing…

AI News · 2024-05-23
AI News—2024-05-23
Unpacking ChatGPT Work: the Agent for a Billion Users

…on. We’ve been covering OpenAI’s research and deployment of agents to all of humanity since Plugins 2023 and Devday 2024 and Codex 2025, and now ChatGPT Work in 2026 seems the penultimate stage of the long journey. Let’s dive in! On July…

Article · Shlok Khemani · 2026-08-04
ArticleShlok Khemani2026-08-04
Sora pushes SOTA

…the implications of secret collusion via steganography among AI agents and the memorization capabilities of LLMs, highlighting the risks as their abilities evolve. A new collaborative scrutiny is suggested to probe the replicability of…

AI News · 2024-02-16
AI News—2024-02-16
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.