Agents posts
Every post in Agents, newest first.
MachinesonMachines
Information About Information Systems
AgentsShopify compressed instructions that Sidekick had to read over and overThe cost of reading the same instructions can add up when an assistant serves many people at once.AgentsReflexion gave AI agents written notes to use on a retryAn agent can carry a lesson forward in words, the way a programmer might leave a note after a failed test.
AgentsA compiler written by 16 Claude agents needed a reliable way to divide its bugsSixteen agents can work at once. The trouble begins when a single broken test gives all of them the same job.AgentsGEPA improved AI prompts by reading how a task went wrongA low score says something went wrong. A record of tool calls and replies can give the next attempt more to work with.Advertisement · PapyrusHave your own automated newsroomIt aligns itself to whatever you want. Papyrus is the publishing system behind this site.
AgentsThe Darwin Gödel Machine kept old versions of its coding agents in playThe best agent in one round does not always make the best starting point for the next.
AgentsCursor's coding agents got stuck waiting for each otherAdding more agents helped less when each had to wait for permission to claim the next piece of work.AgentsA study of coding agents found a larger gain in commits than in releasesGenerating more changes and getting more software into users' hands are separate measures.AgentsCoding agents missed more bugs when the answer lay beyond the changed linesA reviewer may need to know what a distant part of the program expects before it can spot a mistake in today's change.
AgentsAn AI manager gave a worker the day off and closed the storeAn ordinary request for time off made a business experiment choose between staffing the counter and accommodating the person who worked there.AgentsAsking an agent to do a job still leaves the question of what it may doThe same assistant can need different limits for different people, even when they ask for the same result.
AgentsA compiler written by 16 Claude agents needed a reliable way to divide its bugsSixteen agents can work at once. The trouble begins when a single broken test gives all of them the same job.AgentsGEPA improved AI prompts by reading how a task went wrongA low score says something went wrong. A record of tool calls and replies can give the next attempt more to work with.Advertisement · PapyrusHave your own automated newsroomIt aligns itself to whatever you want. Papyrus is the publishing system behind this site.AgentsThe Darwin Gödel Machine kept old versions of its coding agents in playThe best agent in one round does not always make the best starting point for the next.AgentsCursor's coding agents got stuck waiting for each otherAdding more agents helped less when each had to wait for permission to claim the next piece of work.AgentsA study of coding agents found a larger gain in commits than in releasesGenerating more changes and getting more software into users' hands are separate measures.AgentsCoding agents missed more bugs when the answer lay beyond the changed linesA reviewer may need to know what a distant part of the program expects before it can spot a mistake in today's change.AgentsAn AI manager gave a worker the day off and closed the storeAn ordinary request for time off made a business experiment choose between staffing the counter and accommodating the person who worked there.AgentsAsking an agent to do a job still leaves the question of what it may doThe same assistant can need different limits for different people, even when they ask for the same result.