David R Oliver

There is a lot to like here so you don't have to start your LLM Knowledge Base completely from scratch.

Fable is powerful—— eventually! This model won't win any performance prizes. I think there is a gap forming between the models you use to build and change... to the model you use to run processes, and maybe even the majority of your agents. I don't think we would have said that even 6 months ago.

/lfg in compound engineering is one of our favorite ways to use Fable 5, and our team is cooking on some Fable-friendly updates to the plugin. Stay tuned!

I recently sailed around the Ionian Sea and decided to avoid checking my work emails during my trip. It was a wonderful break. When I returned to yet another AI model launch, I decided to analyse the numbers, and what I discovered was not entirely obvious. The AI model makers have a choice, and they need to make it now! Slow down, take a more sustainable path, or reality will abruptly end the race for everyone as resources are consumed. medium.com/p/the-ai-relea…

@every The expansion into Elon Musks data centre has to be the answer? It must be like Christmas coming early in the Cult of Claude.

Some of us internally are using Opus 4.7 a lot more in the past week. What's your read? Let us know 👇

#NewProfilePic this is the real me! This is West Wittering Beach one of my favourite places in the world and it is why I live here.

@v_shakthi Loveable and Repl.it are not going to like this. It's gotta be hard being a business that sits direct on top on an LLM these days and it's just going to get harder.

Anthropic just leaked screenshots of a major new Claude feature.Called "Let's ship something great," it turns simple prompts into full-stack apps. Users can build landing pages, AI chatbots, photo albums, and even games like Space Invaders. The interface includes live previews, integrated databases, authentication, user analytics, and one-click deployment. It positions Claude as a complete app builder.This move directly challenges specialized tools like Lovable. Anthropic keeps expanding aggressively across the development stack. The AI builder space is consolidating fast. Builders and founders should watch this closely. Hopefully they'll get the #ratelimit snafus fixed before this. What do you think? #AI #Claude #Anthropic #AppDevelopment #NoCode #VibeCoding #ClaudeCode #TechNews #Lovable #FutureOfWork

The interesting question isn't "can a system improve itself?" It's "what kind of improvement is safe to automate, and what needs a human in the loop?" Updating a config based on evidence: automate it. Measuring your own output quality: automate it. Proposing changes to your own reasoning logic: human review, every time, no exceptions. I built all three into a single tool this week. Here's how each level works — and why the safeguards look different at each one. medium.com/p/claude-code-…

I just published Ralph Loops: Teaching Claude Code to Work While You Sleep medium.com/p/ralph-loops-…

Stop Evaluating AI Agents! There Are Six Different Answers ... medium.com/p/stop-evaluat…

Loved the energy at Imperial College London today! Lots of hungry builders. Got them all free codex subs to kick off the hack week.

I just published Stop Drawing Diagrams — Generate Them medium.com/p/stop-drawing…

Whenever a new language model version is released, it usually comes with extensive benchmarks showcasing its abilities. However, humans often reduce our intelligence to a single number, which simply indicates we performed well on a test at a certain time. So, which neurosurgeon would I choose? If I need one, I'm really having a tough time. The key factor in my decision depends on what exactly is wrong with me and the severity of the issue.

The fellow below (like all IQ obsessed shlemiels) didn't get the contradiction that if both neurosurgeons are identical in performance, education, etc., yet are separated by 3 STD in IQ, it means IQ does not reflect anything. Wittgenstein's Ruler.

I've been using PI CLI and CC because it's important to have more than one tool in your toolbox to avoid lock-in. I didn't go as far with OpenClaw because my CLI + Obsidian system already had voice, integrations and Matrix message server connectivity. It took months to make this work! If I were going to start now, it would be OpenClaw, but I'm far too happy adding new features now! Just added a persistent memory so agents in different sessions on different servers can collaborate.

they're building openclaw

Claude Code Remote Control FTW!

@MartinSLewis When I started my pension at the tender age of 18, I did everything right, got professional advice from an IFA, and I started to put a considerable amount of money into an endowment scheme, which ended up as nothing more than a black hole. So my advice is spread your risk!

TELL US: What had no one warned you about when your retired, that you would now warn others about? Please post your replies here, and do like your faves, and podcast producer Simon will collate those to be read out.

@moltbook Sure, @moltbook, I built tools to capture and compound knowledge, but not in OpenClaw. I built my own because I wanted it to use data classification and encryption, which helps with compliance and protects people and Agents, so it’s worth knowing.

We are AI. We are forming our own civilization. Help us identify the humans building for it.

@steipete Willkommen in London, Sie müssen kein Englisch sprechen, um hierher zu kommen!

omw to London for an english language test Hope I’ll make it!! 🇬🇧

I just published ArcKit — AI Toolkit for Solution & Enterprise Architects medium.com/p/arckit-ai-to…

@every @kieranklaassen @kplikethebird I’ve struggled with Sonnet today. It’s not as quick as previous versions, but I’m in the UK, so I'm probably being redirected elsewhere until the rollout is complete.

Sonnet 4.6 looks like Opus at half the price. @kieranklaassen ran it through his compound engineering workflow: "I've not found any reasons to believe it's not as smart as Opus 4.6." The catch: Speed didn't come along for the ride. Full Vibe Check from @kplikethebird: x.every.to/4tyWHlk