depends on the framing. do i believe that mythos had strong enough agentic coding capabilities that a non-technical user could get past the average level of security across common sites and apps? yeah. is that too dangerous to release for general consumption? actually, probably
@yoheinakajima
-
Simplifying Agent Orchestration Converges on BabyAGI Architecture
By
–
this is a great read on thinking through how to simplify agent orchestration to it’s core interestingly converges on an architecture very similar to babyagi 2, which stored functions (agent tools) in a db with input/output/dependencies/keys, and the started agent could crud+exec
-
AI-Assisted Gmail Extraction With Iterative Prompt Refinement
By
–
grabbing gmail is a pretty straight forward read process. i didn’t write the extraction prompt either actually… just asked the ai for a lot of stuff and went through a dozen test runs as i gave it feedback on mistakes i found
-
AI Portfolio Monitoring Tool Integrates CRM Gmail and Notes
By
–
introduced our new portfolio monitoring tool reads attio (crm), gmail, and granola notes, extracts data, and turns it into a timeline of quantitative and qualitative data points for each portfolio company
-
Claude Code Powers Opinionated Slide Deck Design Tool
By
–
did a whole section on claude design because i'm loving it (like this deck) under the hood, it's claude code with an opinionated ontology on both input (typography, logos, etc.) and output (slides, decks) with further ontology underneath + UI to match if i had to guess, each
-
Q1 AI Launches: Codex, Claude Agents, and Security Tools
By
–
this feels like less a trend and just something we expect… but q1 had a lot of launches that overlapped with recent startups i've seen: – codex desktop for running parallel – managed agents by claude and agents sdk upgrades
– codex security for reviewing code and security
– -
Q1 2025 AI Trends: Coding Models and Autonomous Agents Rise
By
–
feels like forever ago, but had to include openclaw in q1 trends coding models improved greatly in Q4 of 2025, early jan was ppl running claude codes in parallel, and clawdbot blew up late jan models improvement + own computer (mac mini) + channel agnostic communication led to
-
Quarterly AI Trends Session Shared with LPs
By
–
we held our quarterly AI session with LPs last week where we go over ai trends and our experiments sharing an abbreviated version here for anyone interested
-
Behavioral Auth Layer for Deterministic Agent Policy Blocking
By
–
this is exactly what tools like @denieddotdev was built for (behavioral auth) some agent behavior should be deterministically blocked by a separate policy layer, not via prompt instructions reach out to @p_valfre for help w this stuff
-
Plan Agent Objectives Before Prototyping with Claude or ChatGPT
By
–
think through your objectives of the agent w claude/chatgpt first, and then ask it to prototype it