Google researchers say they can’t imagine being allowed to publish the transformer paper now. Time to return to academia?
LLMS
-
Google releases beginner-friendly prompt engineering guide
By
–
9/ Prompting Guide 101 – by @Google A beginner-friendly resource to master the fundamentals of prompt design. → https://
services.google.com/fh/files/misc/
gemini-for-google-workspace-prompting-guide-101.pdf
… -
Anthropic Releases Comprehensive Prompt Engineering Guide
By
–
7/ Prompt Engineering Overview – by @Anthropic A structured guide with best practices, techniques, and tutorials to improve your prompts step by step. → https://
docs.anthropic.com/en/docs/build-
with-claude/prompt-engineering/overview
… -
Anthropic releases engineering guide for building effective AI agents
By
–
4/ Building Effective Agents – by @Anthropic Core principles for designing agents that are dependable and efficient. → https://
anthropic.com/engineering/bu
ilding-effective-agents
… -
OpenAI Releases Comprehensive Guide to Building AI Agents
By
–
3/ A Practical Guide to Building Agents – by @OpenAI A comprehensive, step-by-step guide from OpenAI on creating and deploying AI agents. → https://
cdn.openai.com/business-guide
s-and-resources/a-practical-guide-to-building-agents.pdf
… -
Experiments Used GPT-4 and GPT-4o; Newer Models Could Improve Results
By
–
And, yes, our experiments used a mix of GPT-4 & GPT-4o (publishing takes awhile). I think we would see much larger results with more recent models, let alone recent agentic tools.
-
Technical challenges in stateful AI agents and memory management
By
–
yeah they do cool stuff around memory. starting to think stateful goes beyond that to tracking changes in the agents capability, etc which I’m not sure if many memory tools do
-
LLM traces masquent un planificateur myope
By
–
“Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning” Reasoning models can write traces that look like real tree search, but this paper shows their decisions are mostly driven by shallow one-step evaluation. They extract search trees from LLM CoT in
-
Architectural challenges in building AI agent loops
By
–
agree. kinda feels like we’re tacking on memory, tools, traces, logs into agent loops but there should be an elegant way to combine them, also relying on crons or heartbeat loops also feels hack
-
Complexity of state tracking in AI agents
By
–
one thing that makes agents more complex is that they generally add capability over time which should also be tracked as part of the state