missed this great thread as well. Prompts are implementation detail – don't leak them, and don't blindly slap them on all the textboxes!
PROMPT ENGINEERING
-
Reverse Prompt Engineering: Notion AI Security Analysis Techniques
By
–
Prompt injection is entertaining, but harmless! https://
lspace.swyx.io/p/reverse-prom
pt-eng
… Presenting the 7 techniques I used to "reverse prompt engineer" the public alpha of Notion AI in 2 hours… and why everyone is **wrong** about the dangers of prompt injection -
Making Tools Editable: Customize Tool Descriptions for Better Agent Performance
By
–
Making tools editable When loading tools, they come with default descriptions. Sometimes, as @brunotorious pointed out, you may want to edit their descriptions in order to get them to work better with agents Now you can: https://
langchain.readthedocs.io/en/latest/exam
ples/agents/custom_tools.html#Modify-existing-tools
… -
ChatGPT Creates PowerPoint Presentations Automatically
By
–
🔥🔥 POWERPOINT HECHOS CON IA 🔥🔥
— Carlos Santana (@DotCSV) 28 décembre 2022
¡POCA BROMA! Pensaba que era una inocentada y hasta que no lo he probado no lo he creído: ChatGPT de los PPTs.
En realidad tiene sentido, tenemos todas las herramientas para convertir en segundos cualquier tema en una soporífera presentación👇 https://t.co/QUwHT4zEpG pic.twitter.com/E6fJGLkPVjPOWERPOINT HECHOS CON IA ¡POCA BROMA! Pensaba que era una inocentada y hasta que no lo he probado no lo he creído: ChatGPT de los PPTs. En realidad tiene sentido, tenemos todas las herramientas para convertir en segundos cualquier tema en una soporífera presentación
-
Dog in Pizza Restaurant: AI Misunderstanding Humor
By
–
me: can I have a dog in a pizza restaurant AI: here's a dog in a pizza
-
OT Too Low Level: Codex Better for Code Refactoring
By
–
OT is way too low level man. too much structure to have to rebuild when codex can already do entire coherent code blocks of refactoring
-
Embeddings as Versioned Documentation for Machine-Readable Code
By
–
my take: Docs for humans, Embeddings for machines Write samples -> get embeddings -> ship with each API/SDK version composable give users 99% accurate codegen can't version foundation models, but can version embeddings If you liked @types
, you'll *LOVE* @embeddings! -
Beyond Copilot: The Next Evolution in AI Developer Experience
By
–
The Big Question in AI-driven developer experience: What's after Copilot? Everyone is convinced this is "just" the beginning but can't articulate what the next killer form factor will be. Increasingly convinced next step change won't be from optimal stuffing context windows
-
Dealing with GPT-3 Limited Context Window Constraints
By
–
how do you deal with the limited context window of GPT3? afaik, ChatGPT a limit of 8092 tokens, whereas GPT3 is lower (3-4k?) any langchain solution to that sort of thing?
-
Language Models Achieve State of the Art on Medical QA
By
–
Language models achieve state of the art on medical QA, demonstrating the power of scaling + prompting. Excited to see the emergent use of language models in domain-specific applications in the next few years!