Jawad ⚡️

7.2K posts

Jawad ⚡️ banner
Jawad ⚡️

Jawad ⚡️

@Signalman23

Software is art and I think I’m Picasso.

🇺🇸 Katılım Şubat 2019
752 Takip Edilen7.2K Takipçiler
Sabitlenmiş Tweet
Jawad ⚡️
Jawad ⚡️@Signalman23·
I built an AI agent that lets me speak to car engines. Dashboard lights waste time and money, so I built a tool that uses AI to diagnose issues. I’ve tested it on 40 cars and it’s hitting 95% accuracy. making workflows faster, smarter, and more efficient.
English
440
942
8.4K
612.7K
WΞNDΞL
WΞNDΞL@bitdeep_·
@cyb3rops "when truly intelligent systems start having creative thoughts outside their training data" the nearest of this is what we call hallucination and we don't allow it.
English
5
0
13
666
Florian Roth ⚡️
Florian Roth ⚡️@cyb3rops·
The more I work with LLMs, the more I think it was a mistake to call this “AI”. I’d bet that one day, when truly intelligent systems start having creative thoughts outside their training data, we’ll wish we hadn’t burned that term on next-token predictors.
English
102
57
624
28.6K
@levelsio
@levelsio@levelsio·
I'm starting to think it has to do with my tech stack why I'm only one doing this Vanilla PHP + Vanilla JS + SQLite is so simple and basic it's hard for AI to fuck up The more complex your stack the higher odds AI (or you!) will make a fatal bug Simple works here
gabriel@g_br_l

@levelsio *how*, though? I'm building a new project that's not even too complex and when doing incremental improvements (not even saying new full fledged features), almost every time something breaks. using mostly 5.5 recently because opus seems to be worse in that regard.

English
38
36
1.2K
187.3K
Tibo
Tibo@thsottiaux·
How do you refer to it
English
726
11
421
168.1K
Shaw (spirit/acc)
Shaw (spirit/acc)@shawmakesmagic·
I asked @Grok Build to make me a RISC-V chip It took a few days but it got it running Debian in emulator. Then I asked it to build a complete PCB and phone enclosure, research real parts on Alibaba and compose a bill of materials. It even made this video.
English
20
11
100
12.1K
Sam Altman
Sam Altman@sama·
the attack at the mosque in san diego is one of the most chilling i have seen. my deepest condolences to the victims, families, and community.
English
946
698
14.8K
1.5M
Jawad ⚡️
Jawad ⚡️@Signalman23·
@NuritNYC @TMTLongShort Worth it for getting them at today’s price and waiting for better os models. Not worth it if expecting os models to rival closed sourced today.
English
0
0
0
42
Nurit Kostov
Nurit Kostov@NuritNYC·
@TMTLongShort thought about getting a serious home setup (rtx6000) to run local models. is it even worth it..thoughts?
English
4
0
1
822
Jawad ⚡️
Jawad ⚡️@Signalman23·
@danliu If $ is present show Apple Pay button…
English
4
1
1.4K
116.7K
Dan Liu
Dan Liu@danliu·
You can trust Apple when they say they care about privacy and know nothing about their users.
Dan Liu tweet media
English
68
260
29.2K
1.3M
Jawad ⚡️
Jawad ⚡️@Signalman23·
@theo If your on windows u can copy the path of the image on your pc and paste it that way.
English
0
0
1
81
Theo - t3.gg
Theo - t3.gg@theo·
Just learned it's literally impossible to paste images into Claude Code over SSH. How do you CLI people live like this??
English
406
18
2.4K
657K
Jawad ⚡️
Jawad ⚡️@Signalman23·
@theo It’s got me worried about OpenAI too if they ever stop aggressively subsidizing things will it end up like this too?
English
0
0
3
635
Theo - t3.gg
Theo - t3.gg@theo·
I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits cut by 40x, despite us doing everything right. I listened to the Claude Code team. I had my issues with their direction, but I trusted them and took them at their word. I will never make that mistake again. Until we see significant change, it is safe to assume any statement from an Anthropic employee is a lie on a timer. The rug will be pulled, no matter how many promises are made beforehand.
English
422
313
8.7K
1.6M
Jawad ⚡️
Jawad ⚡️@Signalman23·
@thegenioo Open multiple VS Code windows with separate folders worktrees for each task each tied to its own Codex thread and backed by git Best way I’ve found to maintain repo hygiene and stop the codebase from turning into a slop maze
English
1
0
1
53
Hamza
Hamza@thegenioo·
@Signalman23 how do you work on multiple projects in that and you miss out on like 100s of features
English
1
0
0
46
Jawad ⚡️
Jawad ⚡️@Signalman23·
@AlexFinn This should have much more views glad to see someone saying the quiet part out loud.
English
0
0
0
132
Alex Finn
Alex Finn@AlexFinn·
I absolutely hate the script companies are using to lay people off in 2026 It’s bullshit and hurts America I’m not picking on Cloudflare here. Every company that has announced layoffs the last 6 months has used this script: “Business is great! We’ve never been more rich! We have so much money we have no idea what to do with it! But AI man, that shit is crazy! Sorry 14% of the company has to go!” They take 0 accountability for poor decisions made. They take 0 accountability for not being prepared for competitors or market conditions. They just blame it all on AI 80% of Americans hate AI and this is the reason. They see CEOs of AI companies saying the world is ending. They see CEOs of regular companies laying everyone off and purely blaming AI If you weren’t as familiar with AI, you’d think it was the worst invention ever This is why every state has people standing outside of data centers protesting, and they don’t even know what a data center is! We have a MAJOR marketing problem in America when it comes to AI, and if this script all of these companies are using continues we’ll have no shot of beating China
Matthew Prince 🌥@eastdakota

An update regarding the future at @Cloudflare. I’ve shared my full message to the team and details on the support we're providing those departing here: blog.cloudflare.com/building-for-t…

English
161
134
1.6K
249.6K
Claude
Claude@claudeai·
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
English
4.8K
12K
130.9K
23.9M
Jawad ⚡️
Jawad ⚡️@Signalman23·
@HowToAI_ But you’re at the mercy of the reasoning of an llm that constantly shifts …???
English
0
0
3
829
How To AI
How To AI@HowToAI_·
The entire RAG industry is about to get cooked. Researchers have built a new RAG approach that: - does not need a vector DB. - does not embed data. - involves no chunking. - performs no similarity search. It's called PageIndex. Instead of chunking your docs and stuffing them into pinecone, it builds a tree index and lets the LLM reason through it like a human reading a book. hit 98.7% on financebench. beats every vector RAG on the leaderboard. no embeddings. no chunking. no vector DB. 100% open source.
How To AI tweet media
English
224
780
6.9K
613K
𝘼𝙡𝙚𝙭
𝘼𝙡𝙚𝙭@ItsAlexhere0·
Is there any trick to avoid Claude Code usage limits?
English
196
1
139
29.7K
Nathaneo Johnson
Nathaneo Johnson@nathaneo_j·
Introducing Series - the AI social network that lives in your texts. For the first time, you can now discover new people directly within iMessage. Live now (thread below)
English
112
53
666
730.2K