Components of A Coding Agent
How coding agents use tools, memory, and repo context to make LLMs work better in practice
Agents, large-language-models, LLMs, python, Reasoning Models
LLMs
ai, ai-ethics, ai-security-research, careers, generative-ai, LLMs, nicholas-carlini, Security, thomas-ptacek
Vulnerability Research Is Cooked
Vulnerability Research Is Cooked
Thomas Ptacek’s take on the sudden and enormous impact the latest frontier models are having on the field of vulnerability research.
Within the next few months, coding agents will drastically alter both the pract…
agentic-engineering, ai, ai-ethics, coding-agents, cognitive-debt, generative-ai, LLMs, podcast-appearances
The cognitive impact of coding agents
A fun thing about recording a podcast with a professional like Lenny Rachitsky is that his team know how to slice the resulting video up into TikTok-sized short form vertical videos. Here’s one he shared on Twitter today which ended up attracting …
ai, ai-security-research, generative-ai, Linux, LLMs, Security
Quoting Willy Tarreau
On the kernel security list we’ve seen a huge bump of reports. We were between 2 and 3 per week maybe two years ago, then reached probably 10 a week over the last year with the only difference being only AI slop, and now since the beginning of the…
ai, ai-security-research, curl, daniel-stenberg, generative-ai, LLMs, Security
Quoting Daniel Stenberg
The challenge with AI in open source security has transitioned from an AI slop tsunami into more of a … plain security report tsunami. Less slop but lots of reports. Many of them really good.
I’m spending hours per day on this now. It’s intense….
ai, ai-security-research, generative-ai, Linux, LLMs, Security
Quoting Greg Kroah-Hartman
Months ago, we were getting what we called ‘AI slop,’ AI-generated security reports that were obviously wrong or low quality. It was kind of funny. It didn’t really worry us.
Something happened a month ago, and the world switched. Now we have real…
Beginner, LLMs, transformers
Mamba4 Explained: A Faster Alternative to Transformers for Sequential Modeling
Transformers revolutionized AI but struggle with long sequences due to quadratic complexity, leading to high computational and memory costs that limit scalability and real-time use. This creates a need for faster, more efficient alternatives. Mamba4 ad…
agentic-engineering, ai, coding-agents, generative-ai, kakapo, LLMs, podcast-appearances
Highlights from my conversation about agentic engineering on Lenny’s Podcast
I was a guest on Lenny Rachitsky’s podcast, in a new episode titled An AI state of the union: We’ve passed the inflection point, dark factories are coming, and automation timelines. It’s available on YouTube, Spotify, and Apple Podcasts. Here are …
ai, gemma, generative-ai, google, llm, llm-reasoning, llm-release, LLMs, lm-studio, local-llms, pelican-riding-a-bicycle, vision-llms
Gemma 4: Byte for byte, the most capable open models
Gemma 4: Byte for byte, the most capable open models
Four new vision-capable Apache 2.0 licensed reasoning LLMs from Google DeepMind, sized at 2B, 4B, 31B, plus a 26B-A4B Mixture-of-Experts.
Google emphasize “unprecedented level of intelligence-p…
Artificial Intelligence, LLMs
TurboQuant: Google’s KV Cache Optimization Explained
A few days ago, a group of researchers at Google dropped a PDF that didn’t just change AI: it wiped billions of dollars off the stock market. If you looked at the charts for Micron (MU) or Western Digital last week, you saw a sea of Red. Why? Because a…