Tom Hipwell

I’ve read a few of these summaries now and I think Simon’s (as always) is best so I’ll link it here.

I’m a massive nerd but I thought this was a really fun post.

I thought there was a bunch of interesting ideas in here as Peter walks through the L1/L2/L3 context design he’s used.

Mario on session durability in Pi, a rough design pattern for resumable agents durability is multi-layered. for pi’s agent abstraction, durability is really just about: store completed LLM responses store completed tool execution results (only the parts t…

The writing on the Claude blog is consistently great, and often becomes the defacto standard for the subject at hand.

Steering is the process of boosting model weights during a session - if you can work out the relationship between concepts and model weight activations (easier said than done) by examining how activations change with slightly varying prompts within the sa…

I’ve been looking at how different agents are handling creds and while looking at the NanoClaw code I learnt that they refactored at the beginning of March to use OneCLI for credential handling.

There’s a pattern described here (prototype big, ship small) that’s valuable.

I have loved following along with Will Wilson’s Antithesis.

Design language is definitely something I struggle with, I find prebuilt skills bundles a little heavy weight (not sure I want an extra 20 commands…) but I’ve bookmarked this to pick through later.

Folks have been having a lot of fun with autoresearch, I haven’t yet tried it out but I’m keen to.

Definitely starting to hear of more places rolling their own systems like this and having success.

Another nice idea from Intercom: So we built a publishing platform.

The truism in the title tells you all you need to know.

There were some wild stats out of Intercom the other week on their Claude authored PR ratio (they are through the 90% mark).

Mileage might vary on how interesting the content is here, I think most of us are familiar with the arguments, but the microsite itself is gorgeous - the use of animations and different modes of interaction is so engaging that I had just had to link it he…

I’m a sucker for a write up on coding agent architecture, I think because I enjoy learning about how the sandboxing works.

About a year ago at Nory we looked at the METR plots for coding performance, at that time the benchmark was predicting an 80% success rate for tasks that take humans about an hour to be hit at the end 2026.

A slightly different benchmark to the popular swe-bench.

This effect has been very noticeable at Nory, folks really want to join and are attracted to the problem and the vibe.

I thought this was really a novel perspective in the oceans of content on gencode out there.

It’s amazing how fast the zeitgeist is swinging around here: Every time you add a “smart” wrapper around model behavior - planning modules, verification layers, output parsers - you’re encoding what you think the model should do.

Kyle Poyar’s writing at Growth Unhinged is normally solid and well researched, plus a handy source of benchmarks if you’re trying to evaluate startups, so it tends to be one I watch out for.

Very exciting to have an open source vision language model this capable.

Vicki Boykis’ year in review is excellent throughout (as her writing always is) but I loved this line in particular: The forking branches of a decision tree in a codebase, are likewise boundless, and the neat part is that there is no right answer.

Fun blog post from Andrew McCalip that attempts to build a model of the unit economics of orbital data centers.

Chad Fowlers take on principles for how the craft of software changes in the AI era: The metaphor I keep returning to is the phoenix: systems designed to burn and be reborn, continuously, without losing their identity.

A short talk from AI Engineer conference in which two Anthropic engineers (Barry Zhang and Mahesh Murag) make the case that you don’t need to build agents.

Andrej nearly summarises where we are today: In this new programming paradigm then, the new most predictive feature to look at is verifiability.

I can never really tell how useful economic analysis are.

Tom McCarthy breaks out the current state of quantum computing.

I enjoy posts like this deep dive from Joshua Rogers on “AI Security Engineers” as amidst so much noise they show the value that agents are adding at the frontier.

Interesting blog post on how database design changes for agentic workloads, first time I’ve seen the phrase “agentic speculation” used to describe agent querying patterns but it seems a good fit:

A very simple thing but this cheat sheet is great, even has simple diagrams for the different merge strategies built in, which is probably the most common area of debate (and confusion) when working with teams.

Nice deep dive on using LLMs for retrieval/recommendation.

I’ve really enjoyed following along with the Embrace the Red prompt injection series over the summer.

Some words on AI strategy from Jamie: Perhaps, the AI-maxi strategy is building vertically integrated operating companies which wield strategic control to own the upside of AI, fundamentally transforming the economics of their business relative to incumbe…

Armin Ronacher (creator of Flask) has a great piece on agentic coding patterns, insightful throughout but largely centered on the uplift you get from effective tool use: Agentic coding’s inefficiency largely arises from inference cost and suboptimal tool…

Elad Gil on AI Rollups: “It just seems so obvious,” said Gil over a Zoom call earlier this week.

Shunyu Yao, a researcher from OpenAI who worked on Deep Research, makes the case for fundamentally altering our approach to benchmarking now we’re in “the second half”: Inertia is natural, but here is the problem.

Simon’s blog is a gold mine.

I think this is a very good post.

Nice explainer that sets out the boundaries of the RL techniques now dominating progress in AI.

YC’s call for startups for the summer ‘25 batch includes a section on Fullstack AI, I’ve written about AI Rollups a few times on this blog, but it looks like the model might now accelerate.

This has been written about in a few places so I’ll keep it brief.

Interesting paper from Cohere, I think this might cause a bit of a storm - basically it’s an investigation into biases towards closed source model companies (OpenAI, Meta, Google DeepMind are named) in Chatbot Arena.

Insightful post from J Betker on the MoE architecture.

This is really good, well worth the investment of your time.

Another AI prediction, but I think this one pinpoints some of the blockers much more clearly.

Well if Kent Beck is doing it: Been vibe coding like a fiend.