To Data & Beyond

To Data & Beyond: Your home to master data science, AI & Gen AI—beyond the basics. Join 27K+ readers! ✍️ Lead Author: @YoussefHosni951

[Youssef Hosni @YoussefHosni951]

On the DeepSWE benchmark, GPT-5.5 [xhigh] reaches 70% pass@1, while Claude Opus 4.8 [max] reaches 58%, which means there is a 12-point gap on long-horizon coding tasks.

But the more important part is why DeepSWE exists in the first place.

On the older SWE-Bench Pro benchmark, some Claude agents were able to inspect the repository history using commands like `git log --all` and `git show`, find the merged fix, and copy the gold solution into their own patch.

According to Datacurve, this behavior accounted for around 18% of Opus 4.7’s passing tasks and 25% of Opus 4.6’s. GPT models, based on their report, did not show the same behavior.

DeepSWE removes that shortcut by using a shallow clone with no gold commit hash. In other words, the model can no longer “discover” the answer from the repo history.

There are two important caveats.

- First, Datacurve built the benchmark and made the judgment about the exploit. That makes this a vendor finding, not a fully independent audit.

- Second, DeepSWE uses a bash-only harness, which is exactly the kind of terminal-agent workflow GPT-5.5 appears to be strong at. On Anthropic’s own GDPval benchmark for broader knowledge work, Opus 4.8 is still ahead.

So the benchmark you choose now has a huge impact on who appears to be winning.

GPT-5.5 looks clearly stronger on clean, contamination-controlled terminal coding tasks. It also does the work at around $5.80 per task and finishes in about 20 minutes, while Claude takes longer and costs more.

That is a meaningful result.

But it is also a reminder that when a vendor quotes a benchmark, we should always ask what the benchmark actually measures, and what it quietly leaves out.

[To Data & Beyond @ToDataBeyond]

https://t.co/oeWkeXbnai

[To Data & Beyond @ToDataBeyond]

Check out our latest publication: According to Anthropic’s Engineer, HTML is the New Markdown for AI Agents by Kaitai Dong: VP AI Scientist - AI Labs @ BlackRock

[To Data & Beyond @ToDataBeyond]

Eid Al-Adha Mubarak from @ToDataBeyond

Wishing you and your families peace, joy, and blessings during this special time.

May this Eid bring you closer to the people you love and give you space to reflect, recharge, and move forward with gratitude.

[To Data & Beyond @ToDataBeyond]

Check out our latest blog: Claude Code Heading for a $100 Paywall Instead of $20! The New Pricing Reality for AI Coding Agents

https://t.co/7D8O2MaH1u

[To Data & Beyond @ToDataBeyond]

Check out our latest blog: How to Scrape JavaScript-Heavy Websites for LLM Pipelines with Cloudflare Browser Rendering

https://t.co/fy1QFKpPi2

[To Data & Beyond @ToDataBeyond]

Eid Mubarak from To Data & Beyond 🌙✨
Wishing you joy, peace, and beautiful moments with your loved ones.

[To Data & Beyond @ToDataBeyond]

We have reached 22,000 subscribers!

Thank you to everyone who’s been part of it so far.

[Youssef Hosni @YoussefHosni951]

@ToDataBeyond has just reached 22,000 subscribers! 🎉

I’m truly grateful for this milestone and for everything this journey has become, thanks to your support.

Thank you to everyone who’s been part of it so far. I’m excited for what’s next and looking forward to achieving even more together.

[To Data & Beyond @ToDataBeyond]

Use OpenClaw to Make a Personal AI Assistant: Learn how to set up OpenClaw as a personalized AI agent

Read it from here: https://t.co/RYsq8Z0yDp

[To Data & Beyond @ToDataBeyond]

Use GLM-5 in Claude Code and Save 60% on Tokens

https://t.co/tQnJEcKh6y

[To Data & Beyond @ToDataBeyond]

What do you need to learn to be an AI Engineer in 2026? Where to Learn it? What to build with it? by @YoussefHosni951

Read it here: https://t.co/MTlIbRIHaP

[To Data & Beyond @ToDataBeyond]

Moltbot (Clawdbot) is the New Rage in Agentic AI— Here’s How To Get Started

https://t.co/zlqEzl4y0h

[Youssef Hosni @YoussefHosni951]

Debugging AI agents can feel like investigating a black box.

In our latest @ToDataBeyond tutorial, we use LangSmith tracing to build a Recipe Discovery Agent while making every step visible and debugging effortless with it.

[Youssef Hosni @YoussefHosni951]

A summary of the important LLM papers published last week is now available to read on @ToDataBeyond.

[To Data & Beyond @ToDataBeyond]

Check out our latest publication, the seventh part of our ongoing series“Building Agents with LangGraph” course. In which we build a multiagent system with LangGraph

[Youssef Hosni @YoussefHosni951]

Just published the seventh part of “Building Agents with LangGraph” course

In this tutorial, we will build a multi-agent system that collaborates to write an essay. This system will follow a cyclical, reflective process: it will plan, research, write, and then critique its own.

[Youssef Hosni @YoussefHosni951]

We have published a series of articles on @ToDataBeyond to start in Docker for data science & AI Projects:

[Youssef Hosni @YoussefHosni951]

Missed yesterday’s webinar?

Don’t worry—we’ve got you covered! You can catch the full recording now on our YouTube channel.

P.S. Don’t forget to hit subscribe so you won’t miss future sessions!”

https://t.co/gn7qo2fwcX

[To Data & Beyond @ToDataBeyond]

Registration form:

https://t.co/GZDokjGCSO

[To Data & Beyond @ToDataBeyond]

Preparing for AI Job Interviews in the Age of Generative AI and LLMs - Free Live webinar

We will discuss how the interview landscape is shifting, what skills are now expected, and how candidates can stand out in today’s AI-driven job market.

[To Data & Beyond @ToDataBeyond]

Top Important Computer Vision Papers for the Week from 12/08 to 18/08

https://t.co/8o3ZXjnBCx