Thomas Sievering

72 posts

Thomas Sievering

Thomas Sievering

@sieveringthomas

Father of one daughter and 27 agents

Germany & Switzerland Katılım Ocak 2016
41 Takip Edilen5 Takipçiler
Mario Zechner
Mario Zechner@badlogicgames·
who here will be a AI Engineer London in April? I'm ready to have more pub visits.
English
23
0
71
5.6K
Mario Zechner
Mario Zechner@badlogicgames·
i give agentic coding workshops every now and then. i have a demo where i let the clanker clone the amp landing page in various ways. just found out their landing page changed and i have 20 minutes before the workshop starts :D
Mario Zechner tweet mediaMario Zechner tweet media
English
13
1
151
10.7K
Thomas Sievering retweetledi
SIGKITTEN
SIGKITTEN@SIGKITTEN·
we're here already
SIGKITTEN tweet media
English
4
6
76
2.6K
Christian Humer
Christian Humer@grashalm_·
@sieveringthomas @johncrickett In the past we just didn't think about one off tools for many things. I do not want to share some of them, because they are too personalized for anyone else to use. Specialized code is often much less complicated. I think most personal tools won't get reused in the future.
English
1
0
0
23
John Crickett
John Crickett@johncrickett·
12 months ago I said this wouldn't age well. So let's check in. AI writing 90% of code? We're not there. Not even close. Sure, there are a few bubbles where adoption is high, in the AI companies themselves and across Silicon Valley. The rest of the world, not yet. Here's what I actually see across the industry: → Some developers don't use AI at all. → Many use autocomplete, and that's it. → A good chunk use chat interfaces as a smarter search engine. → Around 20% are using agents, and mostly just for writing tests. → Around 5% are heavily using AI. Personally I use it a lot. It's genuinely useful for the work I do. I'm in the 5%. But "essentially all the code" by now? That's not the reality most software engineers are living in. The gap between what AI leaders predict and what practitioners experience on the ground is still vast. That doesn’t mean it’s not useful. That doesn’t mean it’s not here to stay. It's just a reminder that timelines from the top of the hype curve tend to compress years of messy, uneven adoption into a single clean narrative. Or as William Gibson put it so well: “The future is already here – it's just not evenly distributed.” Which group are you in?
John Crickett tweet media
English
66
7
120
14.3K
Thomas Sievering
Thomas Sievering@sieveringthomas·
@MingtaKaivo write a style guide for the agent. 'match existing patterns, no new abstractions' is uncomfortable to write but once it's there, taste becomes spec.
English
2
0
1
16
Mingta Kaivo 明塔 开沃
@sieveringthomas solid point. acceptance criteria works for the mechanical stuff. but the CORS fix wasn't hard—my agent just couldn't decide if the solution was clean enough. that's the gap. knowing 'it works, ship it' vs 'let me try one more approach' is still a human call
English
1
0
0
34
Mingta Kaivo 明塔 开沃
agents are terrible at knowing when to stop iterating. watched mine run 47 refinement loops on a CORS fix before I killed it. humans know when the 80/20 point is. that instinct isn't learnable—it's taste
English
1
0
1
47
Thomas Sievering
Thomas Sievering@sieveringthomas·
@coolnalu types are machine-readable specs. the model doesn't infer worse, it just has less to work from.
English
0
0
0
1
Terry Xu
Terry Xu@coolnalu·
I feel Claude Code is much more clumsy on dynamic typed languages - i.e. python.
English
1
0
1
68
Thomas Sievering
Thomas Sievering@sieveringthomas·
@imfrancoierace skill files are definitions, not constraints. limiting what the model does is different from showing it what good looks like.
English
0
1
1
24
Thomas Sievering
Thomas Sievering@sieveringthomas·
your job now is to automate your job
English
0
0
0
21
Thomas Sievering
Thomas Sievering@sieveringthomas·
@bcardarella the gap isn't tooling. it's whether you defined what 'done' looks like before the agent ran.
English
0
0
0
15
Thomas Sievering
Thomas Sievering@sieveringthomas·
@grashalm_ @johncrickett fair. but the 'built for yourself' label doesn't last. most personal tools end up in someone else's workflow before the first PR.
English
1
0
1
32
Christian Humer
Christian Humer@grashalm_·
@sieveringthomas @johncrickett It depends. If u are building long term maintained software, then definitely having a full review is mandatory. If it's a tool you built for yourself then it's fine to not even look at the code most of the time.
English
1
0
1
30
Thomas Sievering
Thomas Sievering@sieveringthomas·
@skirano the test is simple: does it end in a git commit? if it doesn't, all you've done is move the translation problem upstream.
English
0
0
0
86
Pietro Schirano
Pietro Schirano@skirano·
Doubling down on this: the recent wave of AI design tools has done more harm than good. None of them work with real code. Using AI to create yet another layer of abstraction is exactly the wrong move. Design is code, and code is design. And you should care about interactions.
English
13
1
59
4.6K
Pietro Schirano
Pietro Schirano@skirano·
In a few days, we’re shipping something at @MagicPathAI that makes the dream of designing in code with perfect handoff, especially for large teams, finally real. I’ve been in this field for 20 years, and early in my career this would have felt like an ontological shock.
English
49
11
356
31.2K
Thomas Sievering
Thomas Sievering@sieveringthomas·
@plainionist true for the whole loop. what to build, how to verify, when to stop - still on you. leverage is in how precisely you spec those boundaries.
English
1
0
0
10
Seb
Seb@plainionist·
You can let AI write your tests. But you still have to engineer them. You decide: - what to test - how to test - the QA strategy AI generates the code. You engineer the quality.
English
1
0
3
59
Christian Humer
Christian Humer@grashalm_·
@johncrickett Agree. But tbh swarming agents only works for a small subset of my tasks. I do let the agent push the first version directly as PR. And then I iterate with it there. Let it respond with a commit as change. It is simple, persistent and when needed collaborative.
English
1
0
2
43
Thomas Sievering
Thomas Sievering@sieveringthomas·
@fhinkel the tell is whether anything runs when you close your laptop. most people claiming group 2 are still babysitting prompts.
English
0
0
0
149
Franziska Hinkelmann, PhD
There are two types of developers emerging: 1) Those using AI to work faster. 2) Those using AI to build systems that work for them. The first group is vibe coding their way to obsolescence. The second is loop engineering the future. The choice is yours. If you are just a faster version of your 2023 self, you are still a manual operator. True leverage comes from building autonomous loops that scale without your intervention.
English
54
11
184
16K
Thomas Sievering
Thomas Sievering@sieveringthomas·
@headinthebox the eye roll usually comes right before the incident. then suddenly everyone wants your number :)
English
0
0
1
14
Erik Meijer
Erik Meijer@headinthebox·
@sieveringthomas Absolutely. But whenever I pitch this I get eye rolls and are treated like I am a dimwit.
Erik Meijer tweet media
English
2
0
1
127
Thomas Sievering
Thomas Sievering@sieveringthomas·
@mitsuhiko cost to ship dropped. cost to launch dropped even more. the ratio of signal to noise got worse, not better.
English
0
0
0
172
Armin Ronacher ⇌
Armin Ronacher ⇌@mitsuhiko·
I'm trying to catch up with some recent agentic engineering developments and I keep being reminded by this tweet. Barely anything these days is just people sharing ideas, people share products and vibeslopped websites. So much effort goes into marketing. x.com/mitsuhiko/stat…
Armin Ronacher ⇌@mitsuhiko

I wish people would build more useful open source projects and fewer open source products. Everything now has a flashy website and competes for attention, and when it doesn’t get traction the main dev bounces.

English
26
15
270
31.4K
Robin
Robin@solarise_webdev·
@sieveringthomas @GeoffreyHuntley The constant promises of “UBI utopia” are naive and patronising at best Feels like very few people with the wealth and resources to do so are trying to solve real problems instead of vanity projects or trying to cement their place amongst the stars.
English
1
0
1
46
geoff
geoff@GeoffreyHuntley·
it’s undeniable that things are changing at break neck speed but the question remains where is this all heading? anyone who says they know for sure, is full of shit, at this point all I can kinda do is provide colour to binary thinking and pattern match.
English
12
0
57
4.2K
Thomas Sievering retweetledi
geoff
geoff@GeoffreyHuntley·
“porting software has been trivial for a while now. here’s how you do it” (link below)
geoff tweet media
English
5
7
73
16.6K