@marfinxx
@marfinxx
Article

Most developers use Claude Code and LLM agents like an expensive intern...

3 months ago
443
@iiiichigo_chan
@iiiichigo_chan
Article

Your agent follows the prompt perfectly....

3 months ago
316
@_yusufknl
@_yusufknl
Article

> I'm <b><a target="_blank" href="https://x.com/_yusufknl" color="blue">@_yusufknl</a></b><a target="_blank" href="https://x.com/_yusufknl" color="blue"></a> - AI researcher by day, and I break down the math the hype skips. If this is your kind of thing, the follow is the move: I post this stuff wee...

3 months ago
41
@ridark_eth
@ridark_eth
Article

Most people who build a multi-step agent build a line. Step one, step two, step three, each one waiting for the last to finish. It runs. It also runs at the speed of everything added together, and it breaks the moment one step in the middle returns something unusable....

3 months ago
320
@fchollet
@fchollet
Thread

To address the limits of deep learning and avoid stalling, the field of AI started by applying patch (1), which started being demoed 9 months later in December 2024 and has now become completely ubiquitous. However, long term, it is simply inevitable that AI will move to patch (2). <span class="quot...

3 months ago
280
@fchollet
@fchollet
Thread

The "aha" moment when I realized that curve-fitting was the wrong paradigm for achieving generalizable modeling of problems spaces that involve symbolic reasoning was in early 2016. I was trying every possible way to get a LSTM/GRU based model to classify first-order logic statements, and each new ...

3 months ago
166
@ODSAUCA
@ODSAUCA
Thread

🔵Para comprender la baja de la pobreza y la indigencia en la Argentina no alcanza con mirar solo las tasas. En nuestro nuevo documento analizamos su evolución entre 2022 y 2025, un período signado por importantes cambios: aceleración y desaceleración inflacionaria, recesión y recuperación económica...

3 months ago
29
@0xCodila
@0xCodila
Video

Anthropic Engineer: "The biggest mistake in AI right now - people are building graphs and loops without self-improving eval agent We made that mistake at Anthropic - It cost us 2 years" here's how he build it, step by step: step 1 → take 50 real user prompts - run your agent - if it passes 80%+,...

3 months ago
275
@tucksnews
@tucksnews
Thread

LORI BRAY: FAMILY (A WORD FROM THE FATHER) - 8/2/2026 My children, I AM your hope and anchor. Things are about to start. Hold on. I told you the ride gets wild. You are about to see for yourselves just who you are and what you are made of. A fruitful vine that is ripe, an increase in all you've got...

3 months ago
187
Advertisement