Mike Gill

AI Architect & Engineer | Salesforce MVP | AWS ☁️ | Co-founder & CTO @WalknStayApp 🐾 | Startups, AI & ML | Family & Fun | ⚽ Football 🎾 Tennis

[Mike Gill @AgentGill]

Four human skills that matter more than ever:
→ Critical thinking
→ First-principles thinking
→ Judgment
→ Taste
And you already have them.
https://t.co/MuNvP4e23v

[Mike Gill @AgentGill]

Voice chat inside Claude projects, when’s it coming? @AnthropicAI @ClaudeDevs @claudeai

[@levelsio @levelsio]

I decompiled probably my favorite game ever: Battlefield 1942 and I put it on the web with multiplayer for you to play here:

👉 https://t.co/6C8H8KtSaU 👈

(It's the free shareware demo)

It was way harder than the other ports like Quake and DOOM I did because they already had lots of open source projects and work behind them

In case of Battlefield 1942 there was literally absolutely nothing to work on top of, nobody had ever ported it and there was no open source engine for it, nor did the makers ever open source it (like id Software did with Quake 3)

I tried it 6 months ago and essentiay gave up but I tried it today again with Opus 5.5 asking "can you try port the BF1942 demo in this folder to web"

So me and Claude Code (well let's be honest mostly Claude Code) did crazy shit today:
- it disassembled the x86 raw machine code to find 57,000 x86 functions
- it translated each x86 function into a C function (mov eax, [esi+0x110] becomes eax = READ32(esi + 0x110), I have no idea what any of this means btw)
- it outputed 100,000 lines of C
- it then compiled that to WebAsswmbly with Emscripten
- there were 300x Windows and Direct3D functions used which we had to rewrite to WebGL 2 and OpenGL to work on the web
- then we had to build our own network stack so it could connect to our multiplayer server via WebSockets

I have no idea how it did any of this but it did it and it seems to work! 😊

Come play and report any bugs here!

[Martin Fowler @martinfowler]

Rachel's Ramblings:
Why are good developers so wary of agentic development?

https://t.co/a5MmD4N7f4

[Mike Gill @AgentGill]

@andyburnham what did you do today to bring down the cost of fuel for the people?

[Mike Gill @AgentGill]

@ChatGPT hello native plugin support for @excalidraw please 👌🤞 yes I know MCP is exists. Looking for native support like Claude

[Mike Gill @AgentGill]

•Andrej Karpathy writes a new message. He says the difference in how people understand AI increases. He calls this difference a funnel.
•He gives these numbers. About 6 billion people do not use LLM systems. About 1 to 2 billion people use free LLM systems and see small results. About 20 million people use advanced LLM systems for code and maths work and see large results. About 5,000 people use the most advanced internal LLM systems and see very large results.
•The difference occurs for three reasons. People have different problem sizes. LLM systems give the best results in areas that give clear test results, such as code. People have different access levels to the systems. Most people see small progress. A small group of people see very large progress.

[Mike Gill @AgentGill]

@claudeai when can we move chats into projects on iOS app? We’re going backwards not forwards. Why can’t I start a voice chat 💬 in a project on iOS app? Facing some pretty annoying iOS limitations. Thanks

[Mike Gill @AgentGill]

@andyburnham since when is £2.17 per litre an acceptable price for diesel, this simply isn’t working. I mean, it’s frankly disgusting. The government should be stepping in to control this, right? You’re not doing enough!

[Noisy @noisyb0y1]

this one page turns Obsidian + Opus 5.5 + Jev into a system that thinks with you 24/7

built on Karpathy's ideas, it makes your chats 10x faster and cuts 80% of the time you spend on work...

save it and thank me later when you start making a lot of money

[Excalidraw @excalidraw]

Excalidraw CLI released!

Log in to your Excalidraw+ account or use with local files.

You can easily render Excalidraw diagrams to give better output feedback to your agents.

Install today.

[Mike Gill @AgentGill]

Delivered 👌

[Mike Gill @AgentGill]

Really disappointed that the new GPT Live can’t create artifacts from voice chats yet. Feels like such an obvious workflow. Anyone know when that’s coming? @OpenAI

[Mike Gill @AgentGill]

New Claude projects wipe out a lot and leave a feeling of disconnect between different chats and tasks. No voice in projects also seems stupid.

[Andrej Karpathy @karpathy]

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:

Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:

Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:

Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!

In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

[DHH @dhh]

It'll soon be seen as deeply irresponsible to have critical code reviewed by human eyes alone.

[DHH @dhh]

There's nothing kind about letting good people live in a fantasy world that no longer exists. You have to tell them, even if it hurts. Because the sooner they accept reality, the sooner they can adapt to the future.

[Mike Gill @AgentGill]

A stark reminder that how we push forward matters just as much as how fast we move.

[voxium @v0xium]

I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.

[Vercel Developers @vercel_dev]

Jev by @typesafeai is free on Vercel AI Gateway until Sept 25.

Build with the fastest adopted model on the Gateway at no cost.

https://t.co/KsFHUhmaLe
https://t.co/7KsKeZElra

[Thariq @trq212]

We're adding support for AGENTS.md to Claude Code.

Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.

You can toggle this behavior in /config.

[Matt Pocock @mattpocockuk]

Thinking about creating a /pr skill. You invoke it to create a PR that:

- Makes human review as fast and as simple as possible
- Takes the best parts of /show-me by @dexhorthy
- Uses your domain language (from /grill-with-docs)
- Shows evidence that the change works (images, test output etc)
- Assesses merge risk (is it a one-way door, or a two-way door?)

IMO every model/harness I've seen creates garbage PR bodies - needs a skill here.

WDYT?

[WalknStay @walknstayapp]

Phone away. Best friend time. 🐾💛

Tip 5: phone in your pocket, headphones at home. Enjoy the walk together.

Be honest: do you chat to your dog?

All 5 tips:
https://t.co/GsNd5qbb5G

#DogWalking #QualityTime #WalknStay