Techie, indiehacker, solopreneur, developer
Buenos Aires, Argentina
- Tweets 388
- Following 264
- Followers 52
- Likes 726
Javier Benz retweeted
Do you still trust benchmarks or do you just listen to your friends? What makes you try a new model?
946
35
2,080
237,512
Javier Benz retweeted
Here's my conversation with Don Lincoln about some of the biggest open questions in physics, including dark energy, dark matter, the matter-antimatter imbalance, quantum vacuum, quantum foam, and the quest to unify the laws of physics.
Don is a particle physicist at Fermilab who has spent decades working at the frontiers of high energy physics. He is also a great teacher & writer. I highly recommend his courses & books. One of my favorite lecture series he has given is The Evidence for Modern Physics where he breaks down the experiments that validate some of the weird laws of physics we have, and what it would take to validate even the weirder ones.
It's not enough to come up with a beautiful theory. You also have to show through experiment that the theory is likely to be correct. This process often doesn't get the love it deserves, even though it's often the most important and difficult part of the scientific process.
I ❤️ physics.
The conversation is here on X in full and is up everywhere else (see comment).
Timestamps:
0:00 - Introduction
0:49 - Unifying the laws of nature
15:20 - General relativity
32:27 - Electroweak force
44:09 - How particle colliders work
1:02:12 - Higgs boson discovery
1:12:32 - Theory of everything
1:42:17 - Physics of empty space
1:49:41 - Antimatter
2:10:31 - Dark energy
2:14:20 - Dark matter
2:42:56 - Future of physics
207
278
2,093
264,430
Javier Benz retweeted
Since Opus 4.8 is out and more and more designers are getting into Design Engineering, I thought I’d share some of the interaction patterns I use most often:
Use proximity, not just hover. When the cursor gets close, nearby elements can subtly scale and darken based on distance.
It makes interfaces feel more responsive, less binary, and way more alive
onpointermove = e =>
document.querySelectorAll(".dock>*").forEach(el => {
const r = el.getBoundingClientRect();
const t = Math.max(0, 1 - Math.abs(e.clientX - r.x - r.width/2) / 120);
el. style.scale = 1 + t * .5;
});
136
437
9,314
669,580
Javier Benz retweeted
composer 2.5 is, as of today, the best way to visually iterate on frontends.
i was frankly surprised by this, but the speed/quality/value ratio of the model and harness is insanely good. cursor is back!
30
13
429
54,313
Javier Benz retweeted
With Opus 4.8, you can add system instructions mid-conversation without breaking the prompt cache.
More cache hits means lower cost and latency for your API requests.
137
203
3,277
266,666
Grok Build is moving fast
xAI has been shipping Grok Build updates non-stop
If you have not been keeping track, here is what xAI has rolled out up to v0.2.11:
New commands & core features
→ Integrated 𝕏 search and much faster web search
→ Added /export, /login, /usage, and /config-agents
→ Added an interactive read-file viewer with PowerPoint text extraction
→ Added Always-approve mode to streamline permissions
→ Auto-installed shell completions for bash, zsh, and fish
Expanded platform support
→ Added Windows ARM64 and macOS x86_64 support
→ Improved terminal support across Warp, VTE-based terminals, JetBrains, and legacy Windows Console
→ Fixed copy/paste issues across Linux Wayland, WSL, and Windows
Agent & context improvements
→ Subagents now share the terminal backend, scheduler, and monitor across sessions
→ Added proactive system reminders and laziness detectors to keep the model on task
→ Improved context compaction and memory usage for chat history
→ Auto-backgrounds long-running bash-mode commands triggered via !
UX, media & UI upgrades
→ Boosted terminal video playback to 30fps
→ Added multi-image paste, drag-and-drop, and temporary macOS screenshots
→ Added instant loading indicators when switching models
→ Improved clickable markdown links and rendered links inside table cells
→ Smoother plan-mode controls and absolute line numbers in the edit panel
Stability & fixes
→ Increased default retry budget to ~5 minutes
→ Increased Unix ulimits to prevent crashes
→ Hardened background tools to handle timeouts and self-kills
→ Fixed rendering bugs across UTF-8 output, large monitors, Windows contrast, and more
xAI is moving insanely fast
Grok Build is going from early CLI to a serious agentic coding environment very quickly
3,145
3,302
29,168
15,107,674
Javier Benz retweeted
We’ve been putting a lot of effort into making Claude Code more responsive & reliable.
Here’s an update on everything we’ve done:
476
396
13,252
1,672,278
Javier Benz retweeted
How are coding agents changing software engineering?
Yapped for 15 minutes about new Cursor data we published, including:
1. Why lines of code is an imperfect measure of AI progress
2. Balancing intelligence/cost/speed for models
3. Code reviews with "Mega PRs" (1000+ lines)
54
49
813
59,261
Javier Benz retweeted
introducing thermos in cursor
a deep security/correctness audit and a harsh code quality audit, run in parallel on your branch, synthesized into one prioritized list
34
62
1,053
53,900
Javier Benz retweeted
Me using Claude Opus 4.8 to rename a file
Itamar Golan 🤓
1,709
9,143
74,589
44,423,869
Javier Benz retweeted
What are you building?
Share it with the startup community
Get in front of 185,000+ fellow builders
(we'll reshare some of the best if you like :)
460
11
296
252,758
Javier Benz retweeted
Claude Opus 4.8 is now available in Cursor.
On CursorBench, it's able to work much more efficiently than Opus 4.7. We've also found it to be more persistent on harder tasks.
162
147
3,897
306,389
Javier Benz retweeted
bring-your-own MCP servers:
Private MCP servers 🤝 OpenAI products
Your team can keep MCP servers inside your network while ChatGPT, Codex, and the Responses API connect through outbound-only HTTPS.
🔗 developers.openai.com/api/do…
61
60
974
183,268
Javier Benz retweeted
We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code.
Available for all Claude Code users. Install from the plugin marketplace (/plugins).
379
1,675
17,802
2,135,187
Javier Benz retweeted
Naval Ravikant: “Waste Tokens, Save Time."
"Don’t look at tokens either as inputs or outputs. Just look at your time, and look at the final output."
While most people obsess over prompt engineering, Naval says the models will improve faster than humans learn to use them. So instead of optimizing prompts, he brute forces problems with Codex, Claude, and Gemini simultaneously. Burns tokens. Saves time.
And over time, he noticed something surprising: “I found myself typing less and less information and doing less and less work.”
People who aggressively delegate to AI will move faster than people trying to perfectly control every output.
In the AI era: Good enough now > perfect later.
Source: @naval @navalpodcast (May 2026)
15
11
67
4,557
