30 results for "no code"
Claude Code Regression: How to Diagnose and Fix the Recent Quality Drop
Anthropic's postmortem reveals three regressions in Claude Code: reasoning effort, context retention, and verbosity changes. Here's how to diagnose an…
OpenAI's latest AI models, Codex now available on Amazon Bedrock - Reuters
OpenAI's latest AI models, Codex now available on Amazon Bedrock Reuters…
OpenAI’s latest AI models, Codex now available on Amazon Bedrock By Reuters - Investing.com
OpenAI’s latest AI models, Codex now available on Amazon Bedrock By Reuters Investing.com…
KIOKU v0.7.0: completing multi-agent — Gemini and Codex CLI now get automatic session logging
v0.6 made KIOKU's skills agent-portable. v0.7 ports the hook layer too — Gemini CLI and Codex CLI now write to the same session-logs/ pipeline as Claude Code, with masking and security boundaries pres…
Show HN: Knowerage – code coverage for LLM analysis
Local MCP server that tracks AI analysis coverage against your codebase - MTimma/knowerage…
Why my Codex is not working ? Need Help
In my VS code the codex is not working, I restarted, reinstalled, did everything, but not working from this morning, this screen comes and then nothing…
Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features
Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and we…
Anthropic's magic code-sniffer: More Swiss cheese than cheddar, for now
AI vuln-hunter finds what humans taught it to find. Funny that Opinion In retrospect, calling it Mythos made it a hostage to fortune. Anthropic may have hoped that the name implied its AI code securit…
I migrated 16 sites between Linode servers in 1 day with Claude Code
I’ve had an old Linode server hosting my websites now since 2011, and was behind on upgrades and Ubuntu versions, making it harder and harder to upgrade over time. And I had 16+ sites hosted ……
Used a Claude Code skill to fine-tune Qwen3-1.7B from 327 noisy traces, matches GLM-5
Had 327 production traces from a restaurant-reservation agent I wanted to retrain. The plan was to fine-tune a smaller self-hostable model so I could ditch the frontier-API bill. The traces were a mes…
Your Claude Code project dashboard is now on the Mac App Store
‘Never Talk About Goblins’: OpenAI’s Instructions to Codex Have a Weirdly Emphatic No-Creatures Policy
Goblins are expressly forbidden, along with gremlins, raccoons, trolls, ogres, and pigeons.…
Field Notes from a Solo Builder — Shipping the Beloved Claude Code Buddy Into the Wild - Part III
A README mistake, a competing project, a contributor who named the problem I couldn't articulate, and why ASCII art with AI is harder than it looks.…
What are non-leetcode style coding assessments like for big tech companies currently?
Your Claude Code project dashboard is now on the Mac App Store
Floci 1.5.9 - Local AWS emulator now with ELBv2, CodeBuild, and CodeDeploy
OpenAI’s latest AI models, Codex now available on Amazon Bedrock
Show HN: Figma alternative where AI works with vector primitives, not code
You + AI agents, designing directly on the canvas. A free professional vector tool with GitHub-style repositories. Real vectors, fully editable.…
AI Can Find the Code. It Didn't Know How the System Worked
21 bug fixes, two models, same failures. Better LLMs marginally improve things, but still failed on system boundaries and integration.…
Does anyone know why my Z-image base outputs are all this garbage? I'm using a Z-Image turbo workflow (works great with that model) and i swapped out the mode, Vae, text encoder, etc to Z-image base ones from the official sources, what else am i doing wrong?
Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
In many cyber-physical systems, especially in critical applications such as aeroplanes, data to train anomaly detection and diagnosis algorithms is lacking due to data protection issues and partial ob…
You're Already Using AI — You Just Don't Know It
You wake up. Your phone unlocks before you even think about your PIN. You check Slack — the spam filter already ate three notifications you didn't want. You open your IDE, and before you've typed the …
BookStack Moves from GitHub to Codeberg
This post is intended to evolve over time. Status July 27th 2024: Our secondary repos have now been migrated to BookStack on CodeBerg, with the GitHub originals archived with links to the equivalen...…
OpenAI Models, Codex, and Managed Agents Come to AWS
OpenAI GPT models, Codex, and Managed Agents are now available on AWS, enabling enterprises to build secure AI in their AWS environments.…
Lovable launches its AI coding app on iOS and Android, letting users code via voice or text AI prompts, and allowing them to switch between a PC and mobile (Sarah Perez/TechCrunch)
Sarah Perez / TechCrunch : Lovable launches its AI coding app on iOS and Android, letting users code via voice or text AI prompts, and allowing them to switch between a PC and mobile — Apple's recent …
A crazy Claude Code conversation that happened to a colleague the other day
This didn't happen to me but to a colleague. He was working on a Java/Go backend service with Claude Code when it suddenly started hallucinating about Discord.js (a framework that has nothing to do wi…
I’m Jealous of Prompt Engineers (And I’m Not Proud of that)
I see people posting about “I just crossed $10,000 MRR with my SaaS” and sometimes they didn’t even write much code themselves using no-code tools, AI, or existing platforms and it pisses me off. Two …
FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean
Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (\textit…
Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate
The application of large language models (LLMs) in clinical decision support faces significant challenges of "tunnel vision" and diagnostic hallucinations present in their processing unstructured elec…
Time-Series Forecasting in Safety-Critical Environments: An EU-AI-Act-Compliant Open-Source Package / Zeitreihenprognose in sicherheitskritischen Umgebungen: Ein KI-VO-konformes Open-Source-Paket
With spotforecast2-safe we present an integrated Compliance-by-Design approach to Python-based point forecasting of time series in safety-critical environments. A review of the relevant open-source to…