It also auto-drafts responses that match your tone and style. pic.twitter.com/BeBK9UuOpq
— Perplexity (@perplexity_ai) 22 septembre 2025
It also auto-drafts responses that match your tone and style.
PROMPT ENGINEERING
-
AI Auto-Drafts Responses Matching Your Tone Style
By
–
-
Deepseek V3.1 Terminus: Improved Language Consistency
By
–
Deepseek released Deepseek V3.1 Terminus with improved language consistency and minor agent updates for coding and search. Less CN replies for English queries
-
Vibe-coding with Cursor: AI-assisted development and rapid iteration
By
–
Vibe-coding en Cursor iterando y arreglando errores. No es una programación muy compleja hacer escenas así, pero habrá fallos. Y echando un vistazo al inspector de código para ver qué modificar, definir tamaños, etc. se puede avanzar muy rápido. Ahí es donde recomiendo usar un
-
GPT-5 Codex Generates Three.js Minecraft Implementation
By
–
gpt-5-codex when given the prompt "create a three.js basic working version of minecraft, make your own textures, no sound. add some environment to make it more interesting, like sand, water etc.": https://t.co/aQLrJ4ysKg
— Greg Brockman (@gdb) 21 septembre 2025gpt-5-codex when given the prompt "create a three.js basic working version of minecraft, make your own textures, no sound. add some environment to make it more interesting, like sand, water etc.":
-
In-Context Learning: Formal Analysis of Capabilities and Limitations
By
–
5. Is In-Context Learning Learning? This large study argues yes in a formal sense, then shows where it works and where it breaks.
-
AI Agent Tutorials: RAG, Voice, MCP, Multi-Agent Teams
By
–
More AI Agent tutorials here: https://
theunwindai.com AI Agents RAG Systems Voice AI Agents MCP AI Agents Multi-agent Teams Autonomous Game Playing Agents -
LLM Security: Untrusted Text and Prompt Injection Risks
By
–
I'd add another circle to that diagram for the permissions of anyone else who authored text that made it into the context – which often means untrusted external attackers since it's so easy to sneak in malicious instructions for a lot of LLM systems
-
Grok 4 Fast Excels at Creative Coding Challenges Over Language
By
–
The new Grok 4 Fast seems to do well with creative coding challenges ("create a visually interesting shader that can run in twigl, make it like the ocean in a storm", "make a futuristic starship panel for p5js") for a small model but not quite as great in creative language tests pic.twitter.com/C1HZtSNbKP
— Ethan Mollick (@emollick) 20 septembre 2025The new Grok 4 Fast seems to do well with creative coding challenges ("create a visually interesting shader that can run in twigl, make it like the ocean in a storm", "make a futuristic starship panel for p5js") for a small model but not quite as great in creative language tests
-
AI Benchmarks Beyond Training Data: Olympiads and New Metrics
By
–
It is why the gold medals at the various math and coding Olympiads were a big deal: unsaturated benchmarks that weren't in the training data with clear human comparisons. We are down to the various measures of task length (METR), HLE, FrontierMath, vending machine operation…
-
Algorithmic LLM Attacks: Early Research and Discoveries
By
–
One of my favorite early pares on this stuff was https://
llm-attacks.org which algorithmically discovered effective attacks like this one