Search Latent Space

Results for “context engineering”

Articles, conversations, profiles, and grounded writeups.

154 results · Filters applied


Together AI: Making Open Models Practical Across the Stack …aggressively for a ranking. A useful standard should reward engineering that benefits users. The proposed direction is an industry-agreed comparison protocol, drawing on database benchmarking as a precedent, preferably operated… Writeup · Date unavailable	Writeup	—	—
Training LLMs: From Compute Estimates to Working Clusters …while a sufficiently accurate estimate is already useful for engineering decisions. The starting approximation is C ≈ τt ≈ 6PD: training computation C depends on parameter count P and training-token count D. The same work can be expressed… Writeup · Date unavailable	Writeup	—	—
What It Took to Replace a Conference SaaS Workflow With AI Agents …had to happen sequentially. These inputs gave the coding tools context about the system they were meant to build. The agent workflow still needed feedback. One finalist found that an agent had completed its process without launching the app… Writeup · Date unavailable	Writeup	—	—
What Makes an AI Application Worth Building? …why it changes the stakes. The conversation then turns to AI engineering above the model layer, work that augments model capabilities and turns them into useful products. The startup advice is direct: establish that people want the product … Writeup · Date unavailable	Writeup	—	—
What METR’s Time Horizon Measures—and What It Leaves Out …fairness: could a sufficiently skilled human with little prior context succeed using the supplied information? This excludes work that depends on an engineer’s accumulated understanding of a system but leaves that understanding out of the… Writeup · Date unavailable	Writeup	—	—
Why agents need reasoning, inspectability, and better abstractions …strengths and interests. Projects include data collection and engineering, pre-training and some fine-tuning, and agents built with both internal and external models. Evaluation separates three questions that are easy to conflate: - Is the … Writeup · Date unavailable	Writeup	—	—
Why OpenPipe Bet on RL: From Cheaper Tokens to More Reliable Agents …a poor investment for most applications. The main expense is engineering time and slower iteration. Setting up training is estimated to take at least a couple of weeks from a competent engineer, or months for complex reinforcement learning … Writeup · Date unavailable	Writeup	—	—
Windsurf: Building an AI IDE Around Developer Intent …3. Withhold the commit message. 4. Ask the system to retrieve context, infer the intended change, and iterate until the tests pass. This makes software work a masked prediction problem: recover both the missing implementation and the… Writeup · Date unavailable	Writeup	—	—
Xaira’s X-Cell: learning what happens when you turn a gene down …A virtual-cell model might identify a target that protein engineering can address, while patient representations could connect cellular predictions to clinical outcomes. Xaira aims to improve drug-development success rates and halve… Writeup · Date unavailable	Writeup	—	—
Red teaming agents: from malicious inputs to consequential actions …difficulty is asking one model to perform challenging, context-heavy work while tracking a separate set of behavioral rules. Adjusting system prompts and repeating the original objective can help partially. Effective injections exploit… Writeup · Date unavailable	Writeup	—	—