✳flâneur — a map of the web's best reading
Telos — Declarative software, managed for you
usetelos.ai · 1,864 words · saved by 1 readers
Long-running coding agents need more than persistence. Adversarial verification is the feedback loop that lets software begin to maintain itself.
;import{A as ae,B as oe,C as se,D as ce,E as le,F as ue,G as de,H as fe,I as pe,L as me,M as he,N as ge,O as _e,P as ve,R as ye,S as be,T as xe,U as Se,V as Ce,W as we,_ as Te,c as Ee,g as De,h as Oe,j as ke,k as Ae,l as je,m as Me,n as Ne,o as Pe,p as Fe,s as Ie,t as Le,u as Re,w as ze,x as Be,y as Ve,z as He}from ERR: contains `self` is not supported at the top-level of a language. See documentation. interfaces: an analytics service, a log service, a database service, a search service. This had two major effects: - By breaking software down into interface and service-level contracts, Amazon
Explore this link on the map →saved by
related reading
- AddyOsmani.com - Long-running Agentsaddyosmani.com
- Demystifying evals for AI agents \ Anthropicanthropic.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Towards self-driving codebases · Cursorcursor.com
- Would you fly on an AI-coded plane | Hackle's bloghacklewayne.com
- Thoughts on slowing the fuck downmariozechner.at
- The Coming Loop | Armin Ronacher's Thoughts and Writingslucumr.pocoo.org
- The Eternal Sloptember | the singularity is nearergeohot.github.io
- Auto-review of agent actions without synchronous human oversightalignment.openai.com
- StrongDM Software Factoryfactory.strongdm.ai
- Designing agentic loopssimonwillison.net
- Thoughts on slowing the fuck downmariozechner.at