Aktuality
Co se dneska semlelo
Denní výběr toho nejzajímavějšího z vibecodingu a kolem AI. Zdroje stahuju a třídím každý den, tady zůstává jen to, co stojí za přečtení. Nejnovější den je nahoře. Shrnutí píšu česky, ať to dává smysl i bez angličtiny — odkaz vždycky míří na původní zdroj.
-
Stop paying for features you never use. 💸
Grant explains why Pave by Quickbase could be a better fit for small teams that need custom business software without developers, enterprise budgets, or unnecessary complexity. 🚀 !
-
What Happens When Your AI Agent Needs ID? 🤖
Tiago Sada, Chief Product Officer at Tools for Humanity, says World ID could let AI agents prove they’re acting on behalf of a real human. The idea is “agentic delegation”: your bot can enter apps, make requests, or complete tasks, while sensitive actions still require your approval. !
-
Fable's judgement
One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use their own judgement rather than dictating how they should work. The example they gave was testing. You can tell Fable "only use automated testing for larger…
-
Fable 5 je zpět. Nejchytřejší model od Anthropicu #ai #anthropic #fable5 #llm
Fable 5 se po pár dnech vrací pro předplatitele Pro a Max plánu. Je to veřejně dostupná alternativa k modelu Mythos, který Anthropic drží jen pro hrstku vybraných firem.
-
More Than Half the Internet Isn't Human Anymore 🤖
Tiago Sada, Chief Product Officer at Tools for Humanity, says AI agents are here to stay and predicts they could eventually account for more than 99% of internet traffic. Rather than replacing people, Tiago believes these agents will become everyday assistants, taking over tasks like shopping, scheduling, and research while humans focus on higher-value…
-
The website of the future may assemble itself for every visitor
Adobe is experimenting with &;agentic sites&; that generate pages around an individual user&;s intent. At AIEWF, we talked to Carlos Sanchez about the Web's future.
-
This AI Skill Can Debug Your Code Faster 🔁🤖
Stop asking AI to debug once. Give AI a loop. 🤖🔁 Reproduce the issue, try a fix, verify it, repeat. Ryan Carson, Founder of Treehouse and Builder in Residence at Amp, explains how he uses AI agents to fix problems. This turns it into a reliable debugging partner. It’s still not effortless, but it’s getting easier.
-
llm-coding-agent 0.1a0
Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it. I started a new Python library using m
-
Using DSPy to evaluate and improve Datasette Agent's SQL system prompts
Research: Using DSPy to evaluate and improve Datasette Agent&;s SQL system prompts One of this morning's AIE keynotes covered dspy , which reminded me I've been meaning to see if it could help me improve the system prompt used by Datasette Agent - so I fired off an asynchrono
-
How Cursor deploys AI inside the enterprise
Cursor's Pauline Brunet explains how her team of Forward Deployed Engineers help organizations implement agents &; essentially setting up software factories.
-
Can AI Agents Learn From Expert Corrections?
OpenAI and Thrive Holdings built Tax AI, a Codex-powered agent that helps prepare complex tax returns while preserving evidence for accountant review. But the most interesting part is the improvement loop: practitioner corrections become structured signals, Codex investigates traces and evals, and engineers review scoped fixes before anything ships. In this…
-
Efektivní práce s kontextovým oknem - subagenti v Claude Code
V tomhle videu se podíváme na subagenty – co to je, proč jsou skvělý pro úsporu kontextu a zrychlení práce, a jak si je sami nastavit v Claude Code nebo Coworku. Ukážu vám živou ukázku, jak subagenti paralelně dělají research, jak si vytvořit vlastního agenta na míru, a na konci se podíváme i na experimentální Agent Teams, kde si agenti umí povídat mezi…
-
LLM wiki: znalosti, co se udržují samy #llm #ai #knowledgebase #karpathy
Knowledge base, kterou neudržuješ ty, ale AI agent — nové články, poznámky i zápisy ze schůzek se sypou do jedné složky a model si je sám zpracuje a zařadí. Andrej Karpathy tomu říká LLM wiki a v plné verzi ukazuju, jak si ji postavit.
-
Quoting Anthropic
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and will share an update soon. — Anthropic , on Twitter Tags: anthropic , <a href="
-
What's new in Claude Sonnet 5
What&;s new in Claude Sonnet 5 Claude Sonnet 5 came out this morning . I always head straight for the "what's new" developer docs because they tend to have more actionable information than the official announcement post. Anthropic say of Sonnet 5 that "its performance is close to that of Opus 4.8, but at lower pric
-
Have your agent record video demos of its work with shot-scraper video
shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which accepts a storyboard.yml file defining a routine to run against a web application and uses Playwright to record a video of that routine. I've written before about the importance of <a href="
-
shot-scraper 1.10
Release: shot-scraper 1.10 The big new feature is shot-scraper video storyboard.yml , described in detail in Have your agent record video demos of its work with shot-scraper video . Tags: shot-scraper
Tohle není kompletní zpravodajství, jenom to, co mi za den přišlo a přišlo mi to užitečné.
