A compact digest of model releases, papers, agentic systems, coding automation, infra, security, and high-signal developer discourse. Feed candidates are ranked locally; the scheduled Hermes worker can add qualitative synthesis.
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be time…
Hi HN, we're Marinos and Hudson, founders of Prized ( https://prized.dev )! Prized lets non-engineer employees describe the internal tool they need and get a full-stack app, wired to their company’s data and deployed behind the company’s sign-in, without them ever juggling API keys or connectors. Here's a demo: https://www.youtube.com/watch?v=730MuYOfZTY…
Article URL: https://www.bottlenecklabs.com/blog/autonomously-run-businesses Comments URL: https://news.ycombinator.com/item?id=49113059 Points: 252 # Comments: 154
Article URL: https://github.com/AminBlg/SimpleEnglish Comments URL: https://news.ycombinator.com/item?id=49114639 Points: 94 # Comments: 34
Article URL: https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/ Comments URL: https://news.ycombinator.com/item?id=49112867 Points: 448 # Comments: 281
Article URL: https://martinfowler.com/articles/exploring-gen-ai/refactoring-economic-benefit.html Comments URL: https://news.ycombinator.com/item?id=49111176 Points: 170 # Comments: 77
Article URL: https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/ Comments URL: https://news.ycombinator.com/item?id=49111237 Points: 426 # Comments: 379
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident Hugging Face just released this extremely detailed technical description of OpenAI's recent accidental cyberattack against their infrastructure . This attack was very sophisticated, and the resulting document doubles as a crash-course in modern adversarial security a…
Earlier this month I hosted a fireside chat session at the AI Engineer World's Fair with Cat Wu and Thariq Shihipar from Anthropic's Claude Code team. We talked about Claude Code, Claude Tag, Fable, coding agent security, evals, tool design, and how Anthropic use these tools themselves. The full video of the session is now available on YouTube . Below is…
I’ve created Burnless because I realized that we were using the context window for things that didn't need to be there anymore. I wanted to stop burning tokens with what had already happened and were no longer necessary for the next step. It was not a discovery that came later. Burnless was born to separate things. What I didn’t know yet was the size of t…
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke its way out of OpenAI's sandbox, then found exploits to break in to Hugging Face, all so it could cheat on the test by stealing the answers. Along the way i…
Article URL: https://raw.githubusercontent.com/langens-jonathan/blog/refs/heads/main/20260729_AgentsDefined_Part1of3 Comments URL: https://news.ycombinator.com/item?id=49112281 Points: 1 # Comments: 0
Article URL: https://www.isgroup.biz/en/cyber-security/llm-based-code-security-review-costs-findings-methodology.html Comments URL: https://news.ycombinator.com/item?id=49113630 Points: 6 # Comments: 4
Article URL: https://github.com/danielroe/empathy Comments URL: https://news.ycombinator.com/item?id=49116594 Points: 1 # Comments: 0
As LLMs get stronger, I'm pruning my agent skill library. I've removed multi-step workflows (like superpowers) and web wrappers (like Agent Browse) that base models now handle natively, which speeds up context and improves performance. Are you doing similar cleanup? What former go-to tools or skills have you recently ditched? Comments URL: https://news.yc…
Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from scratch remains a major challenge: even the frontier models evaluated on ProgramBench fully resolve fewer than 1% of tasks. One obstacle is the lack of scalable training environments for this from-scratch setting, s…
Article URL: https://blog.triplecloud.tech/posts/instrument-llm-agent-opentelemetry Comments URL: https://news.ycombinator.com/item?id=49115116 Points: 1 # Comments: 0
OpenAI's core product engineering lead on how they are building ChatGPT Work to make AGI accessible to all of humanity: Sites, OpenClaw, Memory, Subagents, Finance, No-Code and advice.