Levi Thomason @levithomason7

Building AI Agents @Microsoft Christian, Husband, Dad at home linkedin.com/in/levithomason Idaho Joined March 2011

Tweets

596
Followers

515
Following

289
Likes

830

Levi Thomason @levithomason7

2 months ago

I can only imagine what the future will bring.

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

8K 11K 150K 27.7M 14K

1 0 0 35 0

View Details

Levi Thomason @levithomason7

3 months ago

@ericweinstein @claudeai @AnthropicAI Had similar total breakdown with ChatGPT last year. Became utterly useless, injecting old memories and producing nonsense. New sessions aren't a guarantee of a clean slate, especially if memory is enabled. Might try nuking all memory and past conversations, starting over.

0 0 1 249 0

View Details

Levi Thomason @levithomason7

4 months ago

@thesayannayak ads 👀

1 0 1 22 0

View Details

Levi Thomason @levithomason7

4 months ago

Sometimes, we can, but should we? 🤣

kitze the 🐐 @thekitze

4 months ago

vibe coders who don’t ship anything showing their agent orchestration setup x.com/FalconryFinanc…

131 377 5K 471K 858

0 0 1 123 0

View Details

Levi Thomason @levithomason7

4 months ago

@zeeg 🤣👍

0 0 0 7 0

View Details

Levi Thomason @levithomason7

4 months ago

@allgarbled I call them "most likely gpt 5.1-3" :p

0 0 0 155 0

View Details

Levi Thomason @levithomason7

4 months ago

@zeeg 💯 the messy llm/agent explosion feels similar to "framework fatigue" and tc39 explosion. we landed in an ok place and I expect the same with this. but yea, can't beat nostalgia 📻

0 0 2 174 0

View Details

Levi Thomason @levithomason7

4 months ago

@zeeg @frosty_pawz Fwiw, I'm tackling the challenge of getting agents to run effectively on large scale Microsoft mono repos. It's definitely not the same game as greenfield/proto agentic work, but it can be done. Like you said, "we'll get there". It's not default capability, but can be wrangled.

0 0 1 40 0

View Details

Levi Thomason @levithomason7

4 months ago

@zeeg I get your point and I often see the same. I think this is true for default behavior and default usage of LLMs/agents. But when used: - in high-value scenarios - with customized flows - and human-staged work Then, I'm only able to dread the day the GPUs aren't running.

0 0 0 27 0

View Details

Levi Thomason @levithomason7

4 months ago

L8, built my first orchestrator 3 years ago Wrote my first neural net 11 years ago LLMs are super powers. Learning to harness token generators is a career.

Juri Strumpflohner @juristr

4 months ago

What's your AI adoption level? (according to Steve Yegge)

286 89 989 2.2M 1K

0 0 0 78 1

View Details

Levi Thomason @levithomason7

4 months ago

@NullTick @hiarun02 My wife still this is crazy

0 0 0 20 0

View Details

Levi Thomason @levithomason7

4 months ago

@Malcolm_Ocean It's impactful, I suspect it was selected for in RLHF

0 0 0 103 0

View Details

Levi Thomason @levithomason7

4 months ago

@mattpocockuk First full 5 days reading and touching 0 files, all work done by agent. Including impact analysis and the blog post. I can outscope and out plan the agent, but I think that's all there is left. Naturally, working on giving it the ability to plan and scope.

0 0 0 51 0

View Details

Levi Thomason @levithomason7

4 months ago

What you're seeing with @karpathy's autoresearch and the explosion of auto* clones is humans building the next layer of automation abstraction. Pushing one more layer down the stack onto the machine. Consider where we were in 2012, where we are, and where were going. Untold capabilities are on the horizon. What does that mean?

0 0 0 59 0

View Details

Levi Thomason @levithomason7

4 months ago

@trikcode Agents have become short-range task completers. They're faster and more efficient than most humans at most tasks. The humans are the ingenuity.

0 0 0 43 0

View Details

Levi Thomason @levithomason7

4 months ago

Again, "Zoom out" Gone are the days of touching files and typing text. We no longer use our brain cycles to plan multi-step text to manipulations. Agents have brought the world where our ideas are self implemented in seconds or minutes. The market is now an idea game.

Andrej Karpathy @karpathy

4 months ago

Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.

830 826 11K 2.5M 5K

0 0 0 47 0

View Details

Levi Thomason @levithomason7

4 months ago

@karpathy @maxbittker Can you add a stop hook to auto continue if needed?

0 0 0 338 0

View Details

Levi Thomason @levithomason7

4 months ago

If you're on this train, you missed the track switch. Jump off, go back & ride again. Claude reads, writes, and organizes faster & better than you. You're the bottleneck. You still drive, direct, and imagine. But gone are the days of hand crafting code and file system artifacts

Simon Wardley @swardley

4 months ago

Software engineers, you have 5 days left. 14 March 2025. Amodei said that AI would write all the software in 12 months. That's five days from now. Prepare to disappear. businessinsider.com/anthropic-ceo-…

273 255 3K 389K 302

0 0 0 92 0

View Details

Levi Thomason @levithomason7

4 months ago

Exactly. @DarioAmodei @AnthropicAI warned of this precise risk as grounds for insisting AI automation should not be used in autonomous combat systems. That said, this is also speculative at this point as I have yet to see confirmation that this scenario took place.