Physicist, Machine Learner
Mountain View, CA
Joined July 2008
- Tweets687
- Following253
- Followers868
- Likes148
I've been using Intent for a while and I love it. It's how I make improvements to Auggie, our CLI agent: have an idea, start a workspace, get to a spec, implement, open PR. Rinse and repeat.
If you want to get more value out of coding agents, Intent it for you.
Very excited to see what Adaption have cooking! Adapting models on the fly feels like it could bring a step function improvement in model quality for real world applications.
Adaption has raised $50M to build adaptive AI systems that evolve in real time.
Everything intelligent adapts. So should AI.
Big day: Augment launched the world's best code review agent, based on the newly minted GPT 5.2. We've been using it internally for a while and it regularly catches bugs that both the author and reviewer miss. Can't recommend it enough.
Introducing Augment Code Review, powered by GPT 5.2. It's the #1-ranked AI code reviewer across precision, recall, and overall quality.
Free for the first week for every paying customer, and free for open source projects.
The past few weeks, we've been evaluating and working with GPT-5 Codex. Ultimately, we decided not to include it in the available models in Augment. Why? 🧵
We found that Codex is an excellent model, but one that would require substantial changes to our prompts to make it work well with Augment's tools and Context Engine. So instead, we will focus on improving the GPT-5 experience (also an excellent coding model).
Excited for Augment to be featured at OpenAI Dev Day! If your codebase is large and messy (who’s isn’t??), you should try augmentcode.com
Cool live Codex demo: in a couple of minutes it built something that controlled the lights in the conference hall through a voice interface.
Excited to explore Sonnet 4.5 new multi-agent capabilities!
Guy Gur-Ari retweeted
Claude Sonnet 4.5 is now the default model for Augment Code.
We’re rolling it out to all customers over the next 24 hours, where it will be available alongside Sonnet 4 (for a limited time) and GPT-5 in the model picker.
Here’s how Sonnet 4.5 compares to Sonnet 4:
Great conversation with @matthewberman and @hnshah today!
Talked about why context is king in AI coding and our unlimited context approach at @augmentcode. Hope other folks get access to the model I'm using as my daily driver soon... 👀
Watch it here: youtube.com/live/e7Wmnslt60M…
I will be going on @TBPN at 1:40pm PT to talk about GPT-5 + Augment Code and share our early impressions. Make sure to tune in!
GPT-5 is here and it’s OpenAI day.
On today’s stream:
@markchen90 (OpenAI)
@gdb (OpenAI)
@thefriley (OpenAI)
@bradlightcap (OpenAI)
@max_a_schwarzer (OpenAI)
@ScottWu46 (Cognition)
@DedyKredo (Qodo)
@zachlloydtweets (Warp)
@rileytomasek (Charlie Labs)
@rauchg (Vercel)
@EnoReyes (Factory)
@guygr (Augment)
@harjotsgill (CodeRabbit)
@clairevo (ChatPRD)
@benhylak (Raindrop)
See you all on the show.
Excited to announce Augment Remote Agents! Once you get used to coding with agents, it becomes obvious that one is not enough. Coding with 5 agents working on parallel on different tasks feels like a superpower. augment.new/
Guy Gur-Ari retweeted
Introducing Remote Agent - cloud-based dev agents with full-codebase context, deep IDE integration, and full toolchain access.
Available in VS Code.
Daunting task of the day: Add a feature to our frontend, which I'm not familiar with. Augment's Agent can answer deep questions like "explain what happens after the user clicks Send" and help me cut through the complexity. @augmentcode ftw
Been using Augment's Agent continuously, and its deep codebase understanding is unmatched. I go from ticket, through design and implementation, to PR and review, all without leaving Agent mode. Haven't had to write a line of code myself in a while, which is a surreal experience.
Guy Gur-Ari retweeted
Augment Agent is now live.
Designed for large-scale codebases — with 200K context tokens, persistent memory, and deep tool integrations, Augment Agent is available in VS Code and JetBrains.
Augment’s agent is #1 on SWE-bench!
🧵We just released the #1 open-source agent on the SWE-bench Verified leaderboard by assembling the best of Claude Sonnet 3.7 and O1.
Open-source repo here: github.com/augmentcode/augme…
Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇
