Mo (meb)

Mo

Designing and building AI systems https://agents.gladio.ai

651 Followers

Recent casts

How I would define an AI agent at the start of 2025: In abstract, a piece of software that can achieve a certain goal, and uses AI to navigate the fuzzy path of achieving that goal. More specifically, a combination of - Goal - Context management - Underlying model - Tools (datastores and functions with effects) - Prompting & self-prompting strategies (including delegating to other agents) Example: A geocoding agent Goal: Parse content from a sentence and geocode it Context Management: Trimmed sliding window. We only need the very most recent messages to get the job done. Underlying model: A simple model like 4o mini is more than enough Tools: A function to search cities with inbuilt query match ranking, and a function with access to a Google Maps geocoding API Prompting: Single turn. The agent should be able to get the job done in a single exchange, or ask the user to clarify the location if needed

  • 0 replies
  • 0 recasts
  • 9 reactions

Howdy! Pleasure to be here. Looking forward to maximising synergies and promoting win win win solutions for ebitda maximisation

  • 0 replies
  • 0 recasts
  • 0 reactions

A friend shared this pretty cringe auto-email. Bless modern recruitment "Picking a single candidate felt a bit like choosing between pizza and tacos - both incredibly delicious, but we could only go with one at a time"

  • 0 replies
  • 0 recasts
  • 0 reactions

Top casts

Had a back and forth with new ChatGPT o1; then asked it say the most intelligent thing it can think of. “Understanding that the quest for knowledge is infinite, true intelligence lies not just in acquiring information, but in synthesizing wisdom to make ethical decisions that positively impact the tangible world and contribute to the betterment of all.” Feels pretty /July worthy to me

  • 0 replies
  • 7 recasts
  • 10 reactions

Classic developer thing; was struggling for over an hour before sleeping on an issue. Woke up and of course found the bug in under 15 minutes.

  • 5 replies
  • 1 recast
  • 20 reactions

A guide on writing smart contract unit tests. Bottom line; Aim for 100% coverage of your methods. Test what changes, who can call methods, events that are emitted and any validations you have. There’s more, but this provides a great foundation and forces you to think through things in a structured way. 4 categories of smart contract unit tests 1. effects - what state changed in the smart contract - did any balances change for related wallets or contracts? 2. permissions - which roles can call method? - who cannot call a method? - is this method callable if the contract is paused? 3. events - what events should be emitted and do they have the expected values? 4. validations - if a given set of conditions are not fulfilled, does the contract revert with a specific error? Be sure to check for the specific error, not just a revert

  • 1 reply
  • 5 recasts
  • 13 reactions

Onchain profile

Ethereum addresses