←
George Lydakis7,436 posts
George Lydakis avatar

George Lydakis

@lydakis

Senior Software Engineer @AWSCloud. Tech talk & coding journeys here.

◷ Joined July 2008▧ 488 Photos and videos
George Lydakis avatar
George Lydakis@lydakis·Sep 8

Like many of us, I started running agents on different machines I own, all connected with Tailscale. I quickly found myself wanting to run builds on other machines without having to start the project on the right machine or manage multiple clones. I had a case where I needed Linux with KVM support, and I already had a Linux box on my tailnet. So I ended up building Errand, a CLI tool that lets you run errands on other machines you own: errand --on linux -- make test With Errand, I can have my agents run Nix builds on my Linux box while I’m coding on my laptop. I can also run my application’s frontend and backend in Docker on my Mac mini, with the dev server forwarded to my laptop when I’m sitting at a café, so I don’t burn through my laptop’s battery. And all that with a very simple CLI. Let me know what you think! github.com/lydakis/errand

George Lydakis avatar
George Lydakis@lydakis·Nov 14

“Give me a hill to climb” is this age’s “Give me a place to stand, and I shall move the Earth.”

George Lydakis avatar
George Lydakis@lydakis·Oct 25

I approve of this arrangement

Post attachment

You can give ChatGPT a photo of an empty bookshelf and ask it to fill the shelves with real books based on what it knows about you. Kinda fun that image gen is so good now!

Post attachment
George Lydakis avatar
George Lydakis@lydakis·Oct 24

So far on the iPhone Duo, Touch ID hasn’t been too bad. You just have to register five fingers, thumb, index, middle on the left, and thumb, index on the right. Then you’re kind of set.

George Lydakis avatar
George Lydakis@lydakis·Oct 22

Got access to Claude Duet today. First impressions are pretty good. It feels like Claude’s projects setup, repackaged for everyday use. Compared with Dots, the UX feels slicker. Compared with Grok Bot, it feels easier to get started.

George Lydakis avatar
George Lydakis@lydakis·Oct 21

This whole process feels very Microsoft-y. Remember the Windows 10 logo wallpaper and all the Fluent design mocks?

Behind the new Apple Music brand identity

1:18
George Lydakis avatar
George Lydakis@lydakis·Oct 20

It’s always GCP

Due to a recent Google Cloud outage, customers may have experienced temporary service disruption on the Revolut app today. The issue has now been fixed, and services are now restored. All our customers’ money and data is safe, and has remained safe throughout this incident. We apologise for any inconvenience caused.

George Lydakis avatar
George Lydakis@lydakis·Oct 15

A realization that keeps resurfacing is that with AI, replacing shouldn’t be the goal, it should be multiplying.

George Lydakis avatar
George Lydakis@lydakis·Oct 15

Most people haven’t caught up with how the unit of delivery has changed. With models like Opus 5.5, you no longer need to break a feature into smaller pieces. You can ship the whole thing at once.

George Lydakis avatar
George Lydakis@lydakis·Oct 14

In other words we ought to touch grass

String theory is what happens when an intelligent system is starved of sensory input and starts hallucinating. Intelligence needs grounding. For this reason, intelligence is practically never the bottleneck to solving impactful problems. The bottleneck is iterated contact with reality.

George Lydakis avatar
George Lydakis@lydakis·Oct 12

> bro just one more AI subscription bro. i swear this one is different bro. just let me try muse wonder full bro. i'll cancel the others next month bro.

Meta has released Muse Wonder and Muse Wonder Full, achieving Artificial Analysis Intelligence Index v4.3 scores of 52 and 56 at max reasoning effort - each a material gain over Muse Spark 1.3 (max) at 48, with a release gap of only 6 weeks Muse Wonder is available for users on Meta’s first-party API, while Muse Wonder Full is currently only available for Muse Code users. Meta notes that each model is designed for personal and professional agent use Congratulations to @AIatMeta, @finkd, and @alexandr_wang on the release! Key Takeaways: ➤ Both models exhibit a material jump in overall Intelligence Index score. Muse Wonder Full (max) improves on Muse Spark 1.3 (max) across all ten Intelligence Index evaluations, gaining 8 points to 56. The largest gains were seen in agentic evaluations: Terminal-Bench 4.0 (+24 points, 33% to 57%), GDPval-AA v2.1 (+176 Elo, 1681 to 1857), and AA-Briefcase (+148 Elo, 1581 to 1729). Muse Wonder (max) gains 4 Intelligence Index points and lands at 52, with notable improvements vs. Muse Spark 1.3 (max) in Terminal-Bench 4.0 (33% to 52%) and AutomationBench-AA (58% to 68%) ➤ Muse Wonder Full (max) places in the top three on six of the ten Intelligence Index evaluations, and is particularly strong in agentic knowledge work and scientific reasoning. In agentic knowledge work, it narrowly leads on GDP.pdf (33%), ranks #2 on GDPval-AA v2.1 (1857 Elo), and #3 on both AA-Briefcase (1729 Elo) and AutomationBench-AA (71%). In scientific reasoning, it tops the CritPt leaderboard at 33% and ranks #3 on SciCode with 63%. This builds on the relative strengths of Muse Spark 1.3 (max), which also showed particular ability in these two domains ➤ Both models use fewer output tokens than Muse Spark 1.3 (max). Muse Wonder (max) and Muse Wonder Full (max) each use around 54k output tokens per Intelligence Index task, down ~10% from Muse Spark 1.3 (max, 60k). This usage is lower than similarly intelligent models Gemini 4 Argon (high, 62k) and Claude Fable 5.1 (max w/ fallback, 78k), but higher than GPT-6.1 Sol (max, 38k) and GPT-6 Astra (max, 27k). Muse Wonder Full (max) uses 16% fewer input tokens per Intelligence Index task than Muse Wonder (max) (6.44M vs 7.69M), meaning it is both more intelligent and more token-efficient ➤ Cost per Task for Muse Wonder (max) lands higher than most similarly intelligent models. Despite efficient output token use, premium API pricing ($4 per million input tokens, $20 per million output tokens) and high input token use (7.69M per task) push Muse Wonder (max)’s cost to $4.52 per Intelligence Index task. This is lower than Claude Fable 5.1 (max w/ fallback, $7.63), Claude Opus 5.5 (max w/ fallback, $5.98), and Claude Sonnet 5.5 (max w/ fallback, $5.46), but higher than GPT-6 Astra (max, $3.26), Gemini 4 Argon (high, $1.99), GPT-6.1 Sol (max, $0.72), and its predecessor Muse Spark 1.3 (max, $1.60). Per-token pricing is not currently available for Muse Wonder Full, so no Cost per Task figure can be estimated at this stage ➤ Both models gain significantly in Coding Agent performance. Muse Wonder Full achieves 68 on the Artificial Analysis Coding Agents Index at max effort in Muse Code, alongside Claude Code with Sonnet 5.5 (max, 68) and Opus 5.5 (max, 66). Muse Wonder (max) scores 63. These represent material gains over Muse Code with Muse Spark 1.3 (max), which scores 54 Other details for the two new models: ➤ Context windows: 1M tokens each, unchanged from Muse Spark 1.3 ➤ Pricing: for Muse Wonder, $4 input / $0.20 cached input / $20 output per 1M tokens. Pricing per token is not yet announced for Muse Wonder Full ➤ Input modalities: text, image, video, and audio ➤ Output modalities: text ➤ Availability: Muse Wonder is available on Meta's first-party API and Muse Code at launch, while Muse Wonder Full is only available to Muse Code users

Post attachment
George Lydakis avatar
George Lydakis@lydakis·Oct 12

This has been really fun to be part of. My dot keeps working on improving the bound, and everyone’s learning from and building on each other’s work in the PRs

We have a lot of these auto-research projects across Github now, so I built a dashboard to track them all, including contributor stats like sports teams :) It tracks new PRs instantly and links to X mentions where everyone seems to be collaborating live. For example I submitted the most pull requests for the integer multiplication bound, but the data shows @dysmemic actually had the most combined time in minutes with the best bound. @che_fe, @dom_scholz, @0xdoug, @lydakis, and more contributors are included. Conditional κ = 9.32058509374204e-4 :) just submitted a new PR app.getsupers.com/auto-resea…

Post attachmentPost attachment