Sabitlenmiş Tweet
i don’t know how i ended up there
Juan Cruz@DevJuanCruz
top 10 mejores frontends argentinos según gemini🤔
English
Tom Piaggio
533 posts
Tom Piaggio
@TomasPiaggio
building autonoma, the most accurate bug finder agent ex googler
San Francisco, CA Katılım Haziran 2010
346 Takip Edilen2.8K Takipçiler
@AravSrinivas at @autonomaai we're building an open source parallel testing agents. that's what we need to ship faster. not a single agent testing a single flow. 1000 agents testing all the flows.
English
A lot of mundane jobs like testing software products and doing quality assessment are on their way out.
Computer@AskPerplexity
We just shipped several upgrades to building web apps with Perplexity Computer. New projects are now automatically tested using Playwright. It navigates your app like a real user to identify and fix bugs before you ever see them. Build, test, fix, ship. All in one place.
English
@cryptopunk7213 texting my code editor is exactly where the industry peaked.
English
anthropic’s openclaw-killer is complete. fucking crazy what they’ve shipped in 4 weeks:
- texting claude code
- 10,000s of claude skills + MCP
- Claude security (autonomous bug-fixer)
- persistent memory (claude never forgets)
- channels (text claude from telegram)
- autonomous cron-jobs
- 1M context window
- new model (opus, sonnet)
- 30+ plug-ins that’ve tanked stocks
- remote control
just insane fucking levels of execution.
Thariq@trq212
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
English
@jayair we basically traded manual debugging for arguing with a chatbot
English
@StockMKTNewz nothing says innovation like another chromium wrapper with a sidebar.
English
if i ask 1000 developers to solve the same problem i'll probably get 1000 different outputs. what's your point? it has nothing to do with the maintainability aspect of the code.
at some point, having maintainable assembly was desirable. when higher level languages came around, that was no longer desirable and performance became the main concern.
what i'm saying is that the same will happen with ai. we'll reach a point where we get very good but hard to read go or rust code in every project.
English
@TomasPiaggio @atmoio If you run gcc on a set of c code 1000 times (given the same flags) you'll get 1000 identical binaries. In your vision running an AI "compiler" on a set of prompts 1000 times will give you 1000 completely different binaries.
Surely you see the problem here.
English
If maintainability weren’t a thing this might be true.
The art of coding has always been the opposite of whatever spaghetti code is. LLMs have not sufficiently demonstrated they understand this concept.
Rohan Paul@rohanpaul_ai
Chamath on how AI agents are making the "10x engineer" distinction disappear because the most efficient "code paths" are now obvious to everyone. Just as AI solved chess and removed the mystery of the best move, AI is doing the same for coding, making the process reductive and removing technical differentiation. "I'm going to say something controversial: I don't think developers anymore have good judgment. Developers get to the answer, or they don't get to the answer, and that's what agents have done. The 10x engineer used to have better judgment than the 1x engineer, but by making everybody a 10x engineer, you're taking judgment away. You're taking code paths that are now obvious and making them available to everybody. It's effectively like what happened in chess: an AI created a solver so everybody understood the most efficient path in every single spot to do the most EV-positive (expected value positive) thing. Coding is very similar in that way; you can reduce it and view it very reductively, so there is no differentiation in code." --- From @theallinpod YT channel (link in comment)
English
@trq212 if this means i have to debug a designer's mcp setup i'm out.
English
@wesbos in the past, i've tried this with the typescript library itself. if a project has typescript it has access to a ton of helper functions to analyze typescript code.
i think this would be a KILLER open source app
English
@TomasPiaggio Oh man yah - I've dreamed of this for a while! What data do I need? Whatever I'm using!
English
Composer 2 vs Opus 4.6 vs GPT 5.4 - a totally unscientific test
> Create a Twitter clone. Use Better Auth, Vite, Sqlite, Drizzle, Typescript, and React with Tanstack Start.
Each one took ~5 mins in plan mode. Each had access to a browser to test.
Composer: 5 mins $6.04 1,250 LOC
Opus: 19 mins $10.43 1,000 LOC
GPT: 22 mins $14.15 2,000 LOC
Opus seems to use the cache WAY more than composer, so it's not really 10x more expensive.
Composer app ran first try. Other two needed a bit of CORS debugging but did work.
Code between all was extremely similar
All three done inside cursor - so Claude Code / Codex may have been different
Models used:
Composer 2.0 (regular, not fast)
Opus 4.6 Medium Thinking
GPT 5.4 Medium Thinking
Wes Bos@wesbos
Cursor just launched Composer 2 - their own model. It's 10× cheaper than Opus 4.6 and supposed to rival it. I've been using it for a few days, I don't have any skewed graphs to show you but from a pure vibes POV I can tell you it's pretty good™ My litmus test right now is if it can build a 3D Printable model with Manifold CAD. I build a Gif zoetrope generator and it did fantastic.
English
in the past i wanted to build like a code search tool for LLMs and i wanted to know for a given function / method on a project, all the references, usages, how it's being used, in what files, etc.
trivial for any lsp and ide.
my use was: i wanted prisma queries to ONLY have the data that was used on subsequent stuff like rendering on react. i've seen too many times queries that have unnecessary fields but because they're many files down and prop drilled, it's hard to know and it's impossible to do with eslint or something like that.
English
@bindureddy i just like seeing how fast glm goes on cerebras. i don't care about the slop
English
@brian_lovin #3 is my favorite part. even though right now claude is super expensive, it'd necessarily go down. margins will get competed away and we all will get cheap models again.
English
Using Cursor again today for the first time in a while. Still using Claude Code, Codex, Conductor, of course.
First: someone needs to rename because the C-named companies are out of control.
Second: fast is good. Composer 2 is good because it's fast. That's all you need to know to at least give it a try.
Third: I am grateful that I can switch between all of these tools in an instant. Little-to-no lock in. I pick the thing that gives me the most intelligence-per-second-per-dollar and am happy.
English
With Offload, @imbue_ai saw a 6x drop in execution times by giving agents the ability to parallelize tasks.
Now open source, and backed by Modal Sandboxes 👇
Imbue@imbue_ai
Your parallel agents needed scalable test coverage yesterday Introducing Offload: a Rust CLI that spreads your test suite across 200+ @Modal sandboxes, freeing your CPU to keep your agents shipping. On our Playwright suite, it took a 12 min run to 2, at $0.08 a run
English
@megastuffs bro you're not vibecoding enough. i paste my envs into claude for it to create the .env file
English
5.4's idea of cleaning up stuff
Thomas Schranz 🍄@__tosh
@mitsuhiko I found gpt 5.4 pretty good at cleaning up stuff from earlier models needs some meta prompting in some cases that help me understand what status quo is and what our options are etc but I expect this to continue w/ better models
English
Tom Piaggio retweetledi
latest newsletter from @GergelyOrosz speaking about code speed and quality. super insightful.
people are shipping faster, yes... but worse products.
that's why we are building @autonomaai.
San Francisco, CA 🇺🇸 English
showed a friend what we've been building.
his reaction: "how is this not DDoSing them"
English
Tom Piaggio retweetledi
@autonomaai is like the sales person that only gets paid when a sale is closed.
we only get paid if no bugs are reach your prod environment.
San Francisco, CA 🇺🇸 English
@swyx hopefully the easter egg isn't just a misconfigured cors policy.
English
Tom Piaggio retweetledi
our startup clients are saying @autonomaai is no-brainer.
they tested no-code/low-code tools but all of them were (1) flaky and (2) required a QA person to set them up.
Autonoma needs neither of those AND we refund you the money if after 30 days a bug reaches production.
We have skin in the game with your downside, upside is all yours.
San Francisco, CA 🇺🇸 English