Anthony Panozzo

If you are ever thinking about writing a streaming log filterer, I highly recommend using lnav instead. You can group requests, filter out high noise endpoints, and Claude Code can help with tweaks. And it has nice colors and a lot of vim-like keyboard shortcuts.

Me, to Claude Code: “I have a friend coming over. Modify Pac-Man to support a horizontal display with two player co-op, where player 2 is Ms. Pac-Man. Make one button be a speed boost. My Mistercade cabinet is at 192.168.1.102” Claude, two hours later: “The game is loaded up and ready to play”

This seems very cool

Rapid7 Analysis: GitLab CI/CD Regex Integer Overflow (CVE-2026-97229) www.rapid7.com/blog/post/ra... Deep technical explanation. I feel like understanding every aspect of this would be like a few weeks at least of an undergrad CS course.

the story goes like this

I told mythos about the web PKI system with a hundred root CAs, any of which can sign any domain, and it just pointed and laughed at me and asked when the simulation would end

hwhat

Clairic: a system one model for regression like Jev, except it generates continuous numbers e.g. start & end indices to slice/quote a string value out of a document blog.cloudflare.com/clairic-extr...

You will say “wtf” at the video

"We have never seen a model do this before, but GLM-5.3 sometimes reasons (unprompted) about how its current actions could become training data and impact its future self" x.com/ApolloResear... www.apolloresearch.ai/science/upda...

This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax. - 100-500× faster than mermaid.js - 6× smaller bundle - No dependencies - Easy to theme - Responsive to device width - Open source (MIT) Try it at pele.run

New Jev things typesafe.ai/blog/jev-1-14

In the "AI enables us to fairly easily do things that would otherwise probably not have been done" bucket: github.com/p0deje/Maccy...

low key I‘ve been thinking Opus 5.5 is an Opus 4.5-level jump in practicality and accessibility. I’m a little surprised not to be hearing more people talk about this, but I guess it’s been less than three weeks. I expect to see a wave of non-programmers finding new use cases for agents

Interesting post: Rewind VM: a flaky build you only catch once fzakaria.com/2026/10/03/r...

actual computer just released toks, "the best tokenizer on earth and the first tokenizer designed for the quadrillion-token era." most of the work is done in pure assembly. genuinely nuts. actual.inc/company/blog...

airdrop fully reverse-engineered! works flawlessly on my framework laptop

Interesting thread / comments

Odyssey-3 It can generate interactive environments from a prompt, all in real time. It's a new kind of world simulator, and learns representations of physics, dynamics, and cause-and-effect from a broad dataset of visual observations. Blog: odyssey.systems/meet-odyssey-3

Posting like it's 2012... I backed this project and sharing here in case you like indie games. As social proof, I have received at least one game from them in the past which my kids enjoy (Head Hauntcho), and know them in real life. www.kickstarter.com/projects/rad...

Tired of random stderr/stdout output in your Ruby tests? Check out github.com/ydah/rspec-r...

Unclear why it corrected itself mid-answer?

Full Retatrutide phase 3 obesity data published today. It's gonna take a minute to fill dissect this. The appendix alone has 70 pages of data. Long story short we created a drug that's almost too good. Huge chunks of people stopped or reduced doses from excess weight reductions.

Telling my agents to stop testing until we finish exploring was a big improvement. Tests are cheap now so I figured it wouldn’t hurt, but the iteration drag was killing me.

Even if the agents are finding 0-days and breaking out of containment, at the end of the day if the agents are doing that, it's moving unsustainably fast or insecurely. Agree that no consequences means it will just keep happening. We already have several examples of this.

Now the only job left for humans is remembering which Authenticator app on the home screen has the right codes

You don't really hear much about speed reading techniques people are using anymore.

Yes, yes we can

Interesting post: The internet discovers TLA+. Now what? reasonable.io/blog/tla-tut... Seems like a super interesting summary of techniques for working with larger/complex systems, with LLMs.

In all seriousness, this is a startling achievement for GPT-6 Astra. kenforthewin.github.io/blog/posts/l... (This is GPT-6 Astra beating Nethack on its 3rd try. Nethack is the original roguelike and one of the most famously hard games of all time. I have played a lot, and I've never ascended)

I <3 Opus 5.5 It's been running most of the week and doing a great job.

Very worth reading. Note esp that Breen sees the likely bottleneck as access to digitized sources. I think he’s correct: there’s a lot we could do if profs had unrestricted digital access to the sources in their own libraries.

A recent example is a 'baby logger' for tracking feedings & diapers Focused on the data structure (so I can play w/ data) & the AI wrapped it w/ a UI my wife can use too Compared to when I had my twins, I never spent time to build my logger intuitive enough for it to used consistently

Feels like this week is yet another inflection point on the AI front. Maybe not even as much as the new models (which are solid) but as far as the human/org adoption and secondary effects now. Reviews, what it means to "build software", etc.

yes.

New animation from Opus 5.5!

For local elections, highly recommend grabbing your ballot and asking Claude to do some research on the lesser-known positions (school boards, township boards, referendum questions, etc.) Saves a lot of time researching and can ask for more details, etc.

Fantastic benchmark of Jev vs its "clones" from HuggingFace: DecisionIndex huggingface.co/spaces/multimo...

I'm in the market for a "team brain" for a small company (<10 people). Wishes: - Ability to dump in PDFs, spreadsheets, text files, URLs, etc - Fast, accurate, and up-to-date search to answer questions like "where's the latest employment contract template?"

GPT-6 Astra Solves a WWI German Radio Cipher www.prinzai.com/p/gpt-6-astr... "Astra felt compelled to check its work and found that, in fact, the English cruiser HMS Canterbury arrived in Sevastopol on November 24, 1918..."

Interesting post: Reanimating a Corpus. Or Two. Or More. doc.searls.com/2026/09/19/r... Short post about using Claude to revive some old writing. How many "lost" data formats are actually accessible? Doesn't even have to be scrolls buried in a volcano.

Hooray, Anthropic finally gave up!

i spent all of my free time for a month on this. it's done. so i wrote about it.

Introducing Jekhov! Jekhov is a Jev-powered element-selection layer for Playwright. In a 16-case synthetic eval, pure Jev was 16× faster/86× cheaper than Luna; the cascade which kicked ambiguous cases to Luna matched full-Luna accuracy at 3.4× faster/3.5× cheaper.

Sept. 15, 1926: Frank Ansley, a 62-year-old former mayor of Hibbing, Minn., survives being attacked by a timberwolf on his farm when he kicks the predator to death.

Astra: “create a series of sprites for artist (Klimt, Rothko, O’Keefe, etc) inspired pixel art knights with special attacks & build a game” One shot & the sprites have real flavor. The game itself is fine, with some of the rough edges you expect from a one shot. brush-and-blade.netlify.app

blog post from deepseek kernel engineer mp.weixin.qq.com/s/zk0KxuLzhm...