Search Latent Space

Results for “context engineering”

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.

1344 results

Bespoke-Stratos + Sky-T1: The Vicuna+Alpaca moment for reasoning

…Memories, Development Challenges with Cascade, Prompt Engineering and Context, AI Integration in Programming, User Experiences with Windsurf Windsurf's Auto-Generated Memories Feature: Users expressed excitement about Windsurf's…

AI News · 2025-01-23
AI News—2025-01-23
OpenAI Sora Turbo and Sora.com

…and updated pricing information to improve user experience. AI Context Understanding Issues Reported: Users have encountered errors like 'The code edit failed to apply' and 'Cascade has encountered an internal error', especially when using …

AI News · 2024-12-10
AI News—2024-12-10
The Evolution of the Agent Harness

…weights that makes the agent work. The environment, tools, context and guardrails that surround the model. Without the harness the model is a brain in a vat. It can take an epistemic action, but needs the harness to actuate that decision in…

Article · Dan McAteer · 2026-08-22
ArticleDan McAteer2026-08-22
OpenAI Voice Mode Can See Now - After Gemini Does

…reasoning tasks. The post did not provide further details or context about the model's capabilities or applications. Many users express skepticism about Phi models, stating they perform well on benchmarks but fall short in real-world…

AI News · 2024-12-18
AI News—2024-12-18
How to train a Million Context LLM — with Mark Huang of Gradient.ai

…AI engineers. Exactly a year ago, we declared the Beginning of Context=Infinity when Mosaic made their breakthrough training an 84k token context MPT-7B. MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav…

Podcast · Latent.Space · 2024-05-30
PodcastLatent.Space2024-05-30
Not much technical happened today

…transformer models on benchmarks. These models boast a 32k context window and minimal memory footprint, handling 1M tokens efficiently. @perplexity_ai teased an upcoming feature with "⌘ + ⇧ + P — coming soon," hinting at new functionalities…

AI News · 2024-10-02
AI News—2024-10-02
12/9/2023: The Mixtral Rush

…multiple channels. This includes its functionality in the context of new and existing models, like Hermes 2.5 and Hermes 2. For instance, Mixtral's encountered performance behaviour in various tests, such as winogrande, truthfulqa_mc2, and …

AI News · 2023-12-09
AI News—2023-12-09
Why the Frontier Ecosystem must be Open — Matei Zaharia and Reynold Xin, Databricks

…data corruption,” why HTAP has been the holy grail of database engineering, and why Databricks thinks LTAP gets most of the benefits by unifying the storage layer instead of collapsing every query engine. We also cover Databricks’…

Podcast · Latent.Space · 2026-06-24
PodcastLatent.Space2026-06-24
Trust in GPTs at all time low

…seems the RAG system naively includes 40k characters' worth of context from docs every time, reducing available context and adherence to system prompts. All pointing towards needing greater visibility for context management in GPTs, which…

AI News · 2024-02-02
AI News—2024-02-02
12/16/2023: ByteDance suspended by OpenAI

…style, attaching an associated artistic movement or era for context, and noting their primary medium. Diverse Representation in AI Generated Scenes: @mysticmarks1 critiqued the policy to diversify depictions of people in AI generated scenes…

AI News · 2023-12-16
AI News—2023-12-16
H100 prices are melting *UP*

…Agent, and @0xSero compressing Qwen3.5-35B enough to fit full context into 24GB VRAM at roughly 1% average performance drop. Quantization and cache work remain key enablers: @iotcoi shipped a TurboQuant vLLM fork with fused Triton KV write …

AI News · 2026-03-28
AI News—2026-03-28
not much happened today + AINews Podcast?

…new features include mail and notification summaries, personal context understanding, and visual search integration. The new iPhone camera button is seen as prime real estate, with OpenAI/ChatGPT and Google search as secondary options to…

AI News · 2024-09-11
AI News—2024-09-11
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.