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.
author:"Ada"
type:podcast
Explore articles, conversations, and the wiki.
Articles, conversations, profiles, and grounded writeups.
Select Apply filters to update results.
Search or filters have changed. The results below still show the previous search; select Search or Apply filters to update them.
1341 results
…Gemini's capabilities LLM personalization Memory and context in LLMs Fine-tuning vs. prompt engineering OpenAI API usage and cost Gemini's shortcomings: A user noted an error in Gemini's VR information, stating that it incorrectly labeled…
…the latter. Model-based evaluation gives an evaluator model a context and a response, then asks it to assess the response. The discussion connects this approach to COMET, Unbabel’s learned evaluator for machine translation. It also revisits…
…IDs and account emails to resolve the issue. Claude 4 Sonnet's Context Crisis Spurs Prompt Engineering: Users report that Claude 4 Sonnet's context window is limited, interrupting conversations, but suggest using the 'continue where you…
…view. The interviewer challenges the forecast with hypothetical contexts of hundreds of millions of tokens and continual learning. The response separates architecture from the learning paradigm. Architecture is the interface between a…
…(CCA-F) exam by Anthropic focuses on practical skills in prompt engineering, context window management, and Human-in-the-Loop workflows. The exam is designed for employees of partner companies, as verified by an attestation process. The…
…tokens, without a causal mask restricting the available context to one direction. The speaker proposes this as mitigation, without suggesting it guarantees that the model learns everything. - Train on reversed facts. In Deductive Closure…
…3 Opus, best of 4 runs. We are working on clustering and flow engineering with Haiku. NVIDIA Earnings and Stock Performance Strong earnings: @nearcyan noted NVIDIA beat earnings six quarters in a row, with revenue up 262% last year to $26B …
…ideas from machine learning, neuroscience, mathematics and engineering to build general AI systems. Google Brain started in 2011 at X, Google’s moonshot factory, exploring how AI could improve Google’s products and services. DeepMind used…
…generation, NVIDIA's GPUs excel in prompt processing at larger contexts, achieving several thousand tps compared to AMD's few hundred. This makes NVIDIA more suitable for complex applications like RAG pipelines and coding assistants. The…
…can see: - Rapid camera motion: One second of video provides context, then recorded actions drive a generated continuation. De Weele argues that skilled players’ fast movements supply useful training examples. - Partial observability: With …
…lots of low hanging fruit to build new agentic interfaces and a context graph/system of record to power Frontier and everything else you do in SMB and Enterprise? yeah. /fin Feb 14 update: This header is usually at the start of the post,…
…Cowork, and asked for an animation. Felix Rieseberg, Cowork’s engineering lead, reports that it produced a looping result. The task looked like design work, but code supplied the means to finish it. Felix sees this pattern repeatedly:…
Sign in with Google, or get the newsletter by email.
Loading Google sign-in…
A conversation with Greg Brockman about OpenAI’s path to AGI, alongside our analysis of GPT-5, Codex, and the shift to agentic coding.
Thariq Shihipar on Claude Code’s next era: prompts, harnesses, plugins, and agents—and what it takes to keep pace with the frontier.
Marc Andreessen on the future of the browser, Pi and OpenClaw, and why this wave of AI feels different.
Priscilla Chan and Mark Zuckerberg on Biohub’s plans for frontier AI and virtual biology, and the ambition to cure or prevent disease.
Anima Anandkumar on modeling the physical world, from weather to fusion reactors, and why physics needs more than language models.
John Platt on automating science, tackling climate change, and how the next generation can contribute in the age of AI.
Anthropic brings interactive apps into Claude with an open MCP standard for richer AI interfaces.
What Sam Altman’s town hall reveals about building startups in the age of AI.
Moonshot’s multimodal model brings competitive coding, native image and video understanding, and parallel agents.
Free. Change your preferences or unsubscribe any time.
Uncheck all to create an account without newsletter emails.
Discover technical newsletters we recommend, then explore Latent Space membership. Both are optional.
Your newsletter choice is optional. How we use your account data.
Please enable JavaScript to sign in or subscribe. You can still read the articles.