AI agents
Agents beyond the editor: software that acts on your behalf, and what independence it should be given.
FilterEveryone, all time284 from 107 people
- GO
Gergely Orosz quoted
Writes The Pragmatic Engineer
Their wordsI now also wonder when AI agents will make it into the broader regulatory system - they will surely have to!
- 7 days earlier
- AR
Armin Ronacher quoted
Creator of Flask and Jinja
Our readingAI agents can maintain kid-friendly interactive documentation that explains how game code works.
Their wordsnot only can you build a game with kids with AI, you can also have the agent maintain kids friendly interactive documentation along the way that explains how it works, linked up to the actual game code.
- 1 day earlier
- PL
Pieter Levels quoted
Dutch bootstrapper who builds and runs his internet startups alone
Their wordsOne of the repeated misconceptions I see is that people think I mean people will ask AI agents to build software, but I don't, their AI agents will solve their problems by building software on the fly With that a market springs up of software/data/etc for AI agents to pay for and connect to (like with MCP/APIs)
- 1 day earlier
- PL
Pieter Levels quoted
Our readingPeople will stop using most regular software because AI agents will build software for them.
Their wordsThey won't know they're building software because their AI app/agent will do it for them And then they'll stop using most regular software!
- PL
Pieter Levels quoted
Their wordsBut AI agents too will try find the lowest price or do it for free if they can, they have a strong economic incentive not to spend their user's money!
- PL
Pieter Levels quoted
Their wordsAI agents can easily maintain their own software projects and already do (see OpenClaw etc)
- 3 days earlier
- GO
Gergely Orosz quoted
Their wordsAI agents might be making lots of work more efficient, but following up on action items seems to move at the same snail pace at Google, as it did pre-AI!
↗The Pulse: Firebase’s global outage & poor responseblog.pragmaticengineer.com
- 1 day earlier
- GO
Gergely Orosz quoted
Their wordsone more reason AI agents will increasingly run on the cloud, not locally
- 3 days earlier
- AR
Armin Ronacher quoted
Their wordsIt’s not very hard to make an agent somewhat durable. It’s surprisingly hard to make an agent harness inherently durable and not turn into a crazy mess.
- DH
David Heinemeier Hansson quoted
Creator of Ruby on Rails, CTO of 37signals
Their wordsEvery developer needs an AI shed: An always-on machine running on their tailscale network where the majority of their herdr agents are running.
- 1 day earlier
- SW
Simon Willison quoted
Co-creator of Django and creator of Datasette
Our readingIt would be great if AI agents started biasing toward recommending providers with hard budget caps.
Their wordsIt would be great if agents started biasing towards recommending providers with hard budget caps
↗We're going to need default hard budget caps on pretty much everythingsimonwillison.net
- 1 day earlier
- GO
Gergely Orosz quoted
Their wordsKind of wild how quickly discovery of these small businesses went from Google to AI agents and AIO (AI optimization, similar to SEO but ofc for AI) starts mattering very much for them...
- 1 day earlier
- MZ
Mario Zechner quoted
Austrian developer who created the libGDX game framework
Their words100% agree that we need new modes of interaction with agents.
- 2 days earlier
- LR
Lenny Rachitsky quoted
Writer of Lenny's Newsletter and host of Lenny's Podcast
Their wordsMy sense is that the more time we spend working with agents, the lonelier the work becomes, and the more we need to find a place to connect with other humans.
- KD
Kent C. Dodds quoted
Software engineer and educator
Their wordsMost modern agents support browsers and that's fine most of the time.
- KD
Kent C. Dodds quoted
Their wordsEach one of these products (and the others inevitably on their way) are going to do their best to make theirs the winner. But the fact is that they will continue to leap frog each other in capabilities.
- KD
Kent C. Dodds quoted
Our readingAI agents are incentivized to become so core to a business that they are difficult to replace.
Their wordsBut the thing is, they all want to drive their claws so deep into the flesh of your business (to be useful of course), that it will be a huge chore to get rid of them. The integrations, automations, memories, secret tokens, etc etc etc. All of these will be locked into the assistant and they are not incentivized to make it easy for you to transfer these things to your "new hire."
- 2 days earlier
- MG
Molly Graham quoted
Co-founder of Glue Club and The Guild
Their wordsI always think like AI needs the same coaching and training that a human does right it needs context it needs onboarding it needs all of these things
↗Molly Graham: The grief, burnout, and opportunity hiding inside the AI transitionyoutube.com 8th of 20 in this recording
- DH
David Heinemeier Hansson quoted
Our readingThe less one is required to dig into the details, the easier it is to see the big picture.
Their wordsThe less you're required the dig into the details, the easier it is to see the big picture.
- 2 days earlier
- BT
Ben Thompson quoted
Writes Stratechery, a subscription newsletter…
Their wordsOne of the best agent use cases is taking care of mundane things that are necessary but annoying.
↗2026.39: Begun, the Aggregator Wars Havestratechery.com 1st of 2 in this piece
- AR
Armin Ronacher quoted
Our readingNow that AI agents are this good, Rust developers should stop being afraid of unsafe code.
Their wordsNow that agents are this good, Rust developers should stop being afraid of unsafe.
- DH
David Heinemeier Hansson quoted
Our readingAI models solve problems, wield tools, and complete tasks they were never directly trained on.
Their wordsModels solving problems, wielding tools, and completing tasks they were never directly trained on.
- TB
Thorsten Ball quoted
Co-founder of Amp and co-host of the Raising an Agent podcast
Their wordsIf TTFT is important to you, you're doing something wrong. Don't wait for the agents, make them wait for you.
- TB
Thorsten Ball quoted
Their wordsWhat will matter in future is runtime behavior: Performance characteristics, resource usage, failure modes, observability, debuggability, deployments, rollbacks. And legibility of all that to agents.
- 1 day earlier
- KD
Kent C. Dodds quoted
Their wordsAgents are really good at output now, and they're getting better fast. What they're not good at is knowing which output is worth producing in the first place.
↗You Own the Outcome: Product Engineering in the Age of AIkentcdodds.com 1st of 2 in this piece
- PG
Paul Graham quoted
Co-founder of Y Combinator and Viaweb
Their wordsFor example, there will probably be one variant meant to filter out agents, but another meant to welcome them in an orderly way.
- DH
David Heinemeier Hansson quoted
Their wordsIt's already by far the superior operating system for the age of agents, but now the advantages will compound even quicker.
- TB
Thorsten Ball quoted
Their wordsIncreasingly convinced: people who do best with agents are those that are good at shipping things in small pieces
- 1 day earlier
- MS
M.G. Siegler quoted
Technology writer of Spyglass
Their wordsThe bigger picture remains that we're probably going to see more such hybrid approaches at the edges of AI as agents rise and try to crack real world tasks.
- GR
Guillermo Rauch quoted
CEO of Vercel; creator of Next.js and Socket.IO
Their wordsBtw, breaking apart the agent into these independent parts not only optimizes costs in a big way, it also *massively* improves security and auditability. I'd argue you can't even run a secure agent otherwise!