Jason Pecho

CTO of Look North World, working in #UEFN, ex Disney, EA, experienced game dev - Enjoy IPAs, both digital and physical. Man of the pizza

[Jason Pecho @alk3ovation]

@UnrealEngine Legend of Zelda: a link to the past

[Jason Pecho @alk3ovation]

@tomjank I thought this looked familiar 😆

[Jason Pecho @alk3ovation]

@Richytoons @LetKyle Whoa this looks awesome!

[Jason Pecho @alk3ovation]

@LiyabilityJP @TimSweeneyEpic Thanks! We’ve been able to repro it now so we’re working on a fix. We put in a temp stopgap that will stop matchmaking new players into servers after some minutes so that these busted servers spin down much more quickly. A bandaid, hopefully short lived.

[Jason Pecho @alk3ovation]

@LiyabilityJP @TimSweeneyEpic Working hard to resolve it!

[Jason Pecho @alk3ovation]

Is it just me or is video playback broke on #x - I can’t play videos anymore. They just spin endlessly

[Jason Pecho @alk3ovation]

@jscottcameron I do a lot of planning with the AI first. Cursor has a plan mode. Bezi currently doesn’t. So I just do the planning in a thread an have it great a page that we iterate on together. Then I ask it to create a phased implementation plan so I have checkpoints to go back to if it fail

[Jason Pecho @alk3ovation]

Pretty spot on to how I feel. I don’t feel code writing atrophy yet but I’m definitely at the 80% AI code and 20% hand written point.

Code is cheap now and getting to see multiple versions of a system before committing is powerful.

I’m here for it

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Jason Pecho @alk3ovation]

@jscottcameron For Unity, I’m using Bezi. For UEFN and Roblox and web, I’m using Cursor. Haven’t done much in UE5 lately but if/when I do, I’ll look at either setting up cursor or see if Riders AI is any good.

Bezi is nice kuz it has full access to your project and can modify stuff in editor

[Jason Pecho @alk3ovation]

@insaneUEFN Very cool Jerome

[Jason Pecho @alk3ovation]

I haven’t played a ton of games this year but Skate Story is hands down the best of the year IMO

[Jason Pecho @alk3ovation]

@tomjank Your experience with the way you think about building stuff in scene graph will translate nicely to Unity. Unity was the OG commercial scene graph. I would guess epic took a lot of inspiration from Unity’s Game Objects and Components. Jump in!

[Jason Pecho @alk3ovation]

If you have a couple hours this is a great listen for any engineer! #gamedev

[Łukasz | Wookash Podcast @wookash_podcast]

You will need to 0.75x the speed on this one.

The raw speed of @mmalex mind is insane. Together with @antovsky we chatted about game architectures, building complex projects with editor-first mindset and more!

Both of these fine gentlemen have worked together at @mediamolecule and they share incredible engineer ethos. Loved the talk!

Anton & Alex thanks a lot for joining me!

[Jason Pecho @alk3ovation]

This has definitely saved me time! I don’t have to search for APIs and figure out what the generic compiler warning is when I make a typo.

[Jason Pecho @alk3ovation]

As someone who has never typed well - my biggest use of AI in programming is to describe almost exactly what I want the AI to do. I then review the code and make necessary changes manually. I do this in small chunks over and over again. So the AI is more acting as my input device

[Jason Pecho @alk3ovation]

I find UMG and Verse UI so much more intuitive to layout than css. That is all #gamedev

[Jason Pecho @alk3ovation]

@LiyabilityJP We’ve been getting this same thing. Ours side the word “beotch” was found in the code but it was just a string to message conversion function. Renaming that function and the params and resubmitting fixed it. Seems like whatever’s being used to moderate text automatically is broke

[Jason Pecho @alk3ovation]

@LenkaAccount Branches finally!!

[Jason Pecho @alk3ovation]

@natereesedev Since when can you modify Niagara Params from verse? SG only?

[Jason Pecho @alk3ovation]

@natereesedev Heyoooo