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.
721 results · Filters applied
…tool streams, and splitting endpoints for standard vs 1M context sessions; a second thread details the surprisingly large amount of model-specific parser and harness work needed to onboard an OSS model cleanly (details). Distribution and…
…real-world attacks on chatbots and voicebots, including contextual manipulation, adversarial attacks, ethical compliance, polymorphic testing, and social engineering. The platform aims to identify vulnerabilities and provide actionable…
…acquired Jina AI to deepen multimodal/multilingual search and context engineering in Elastic’s agentic stack (tweet). Gemini crossed 1.057B visits in Sept 2025 (+285% YoY), its first month over 1B visits (@Similarweb). State of AI 2025 is…
…5k tokens of data such as tool schemas, memory CRUD protocols, context engineering, and basic guardrails. The leak includes external data sources like finance and arXiv, and has been independently verified across multiple platforms,…
…its timestamp accuracy and mentions it hallucinates with longer contexts, though it remains competitive in general WER (Word Error Rate) with models like Whisper medium. There is a consensus that Google's Gemini models are not open-sourced,…
…user intervention, leading to a perceived shift in software engineering workflows. One commenter corroborates the claims, reporting that Opus 4.1's efficient sub-agent context management enabled complete refactoring (e.g., god class…
…specifically naming “OpenAI 5.4 and 5.5” @dee_bosa. A nearby contextual tweet from Apoorv Vyas explicitly linked “the Cerebras IPO” to a Stanford discussion on compute scarcity, inference demand, routing, and open source, suggesting the IPO…
…attempting to merge two MistralCasualML models with differing context sizes, highlighting a tensor size mismatch. Community members were seeking solutions to this and related issues. JSPyBridge Facilitates Cross-Language Engineering:…
…work, emphasizing design decisions over mere prompting or AI engineering. Aider Session Resumption Saves Context: Discussion arose around resuming Aider sessions to maintain context memory, using the --resume flag, but with incomplete…
…for reasoning and advanced technical concepts, high-quality engineering data, and an improved optimizer and training recipe. This produced a stronger foundation for the SFT and RL stages that followed.We then used Grok 4.5 to regenerate the…
…seconds (152k views) Cohere transforming insurance with large context summarization and knowledge assistants (4k views) Runway partnering with Musixmatch to make lyric video creation and customization easier (8k views) Prompt Engineering as…
…both sides, as it incrementally mak[es] agents easier to run. Context Engineering Seeded by ByteDance: Members discussed Context Engineering, with one calling it Latent Space Engineering, linking to a post on Hacker News. Reference was made…
Sign in with Google, or get the newsletter by email.
Loading Google sign-in…
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.