Šis puslapis nėra tiesioginis — žinutės atnaujinamos pagal tvarkaraštį. Paskutinį kartą atnaujinta . Kito atnaujinimo laukiama apie . Laikas rodomas Vilniaus laiku (EET).
AI aprašymas Tamsiame fone matomas naudojimo juostelės indikatorius, rodantis, kad visų modelių limitas išnaudotas 83 proc. ir atsinaujins po 11 valandų bei 10 minučių.
Sugeneravo dirbtinio intelekto modelis qwen3.8-27b-dk:latest (vienu ėjimu, be samprotavimo biudžeto). Žmogus netikrino.
Pas mane Codex'as imasi tvarkyt našumą ir resursų efektyvesnį naudojimą, įskaitant ir memory window; net smalsu ką pavyks jam padaryt, kai harness'as lyg minų laukas :D
gan dažnai security-review'er pasišaukia plugin'ą :)
AI aprašymas Tekste pateikta žinutė, kurioje nurodoma, kad buvo atrasta nauja „breakthrough“ (pertrūkis) padaremo, kuris veikia ne tik su AAM ir QH, bet ir su „agent to agent cooms“.
Sugeneravo dirbtinio intelekto modelis qwen3.8-27b-dk:latest (vienu ėjimu, be samprotavimo biudžeto). Žmogus netikrino.
su mano aiagentmemory.dev draugas uzsuko agentu swarm 😄 naudoja memory kaip komunikacija tarp agentu, vienas po memory kapstosi, kitas adr tikrina trecia audituoja ir pranesineja problemas, self healing 🙂
pasirodo "poll" uztenka tam net nereik realtime notifications 🙂
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally bene
SwarmWorld: Stigmergic technological evolution in societies of language-model agents
Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social organization. Language-model agents offer a new substrate for this process, yet most multi-agent systems rely on direct conversation, predefined roles, or centralized workflows. It remains unclear whether decentralized agents can build functional technologies and outperform independent search. Here, initially homogeneous LLM agents in SwarmWorld self-organize without assigned roles or recipes into evolving technological societies. Agents explore a spatial environment, process resources, test materials, construct persistent artifacts, and write executable controllers evaluated by a deterministic simulator under unseen disturbances after the agents are removed. SwarmWorld splits cognition from consequence: agents propose architectures and controllers within fixed action and material schemas, while the simulated world determines function. Sh
