Sourcegraph's profile picture. Agentic coding (@AmpCode) and code search, trusted by the world's best software teams.

Sourcegraph

@Sourcegraph

Agentic coding (@AmpCode) and code search, trusted by the world's best software teams.

مثبتة

No more waitlist — @AmpCode is now available to everyone!


Build Crew Live: Episode 4 with @ColleenMBrady 00:00 - Introductions and "Four Corners of the Western World" 01:48 - What We Changed Our Mind About This Week 04:35 - Reading Physical Books Again 06:20 - Claude vs ChatGPT for n8n Workflows 14:20 - Database Test Data Generation…


Sourcegraph أعاد

Build Crew Live: Episode 5 (full episode) Timestamps: 0:00 - @grahammcbain kicks things off 0:56 - Weekly question: What changed your mind this week 2:46 - Discussion on agent task complexity and incrementalism 7:00 - @thorstenball's take on ads and business models 11:00 -…


Sourcegraph أعاد

Deep Search is how code search should be. Shipping today in Sourcegraph Code Search, after heavy use inside our customers Indeed, Stripe, and more.


The founder journey with Sourcegraph CTO Beyang Liu and ex-CEO of Focal Systems Francois Chaubard at Stanford's Hazy Research Lab. They talk about coding agents, whether scale is all you need for AGI, and how industry and academia will advance from here: youtube.com/watch?v=hR6zyA…

Sourcegraph's tweet card. Sourcegraph - Beyang Liu (CTO) | Stanford Hidden Layer Podcast #101...

youtube.com

YouTube

Sourcegraph - Beyang Liu (CTO) | Stanford Hidden Layer Podcast #101...


Sourcegraph أعاد

Developers approved 74.3% of code written by Codex compared to 73.7% for Claude Code, according to data from more than 300,000 pull requests collected by startup Modu Sourcegraph's Amp agent had the highest acceptance rate at 76.8%

OpenAI's efforts to catch up with Anthropic's code-writing AI seem to be working: OpenAI's Codex has pulled ahead of Anthropic's Claude Code assistant by some measures, and its popularity with developers is catching up too, based on new data from Modu: theinformation.com/articles/opena…



Sourcegraph أعاد

OH: "Deep Search gets more unsolicited fan mail than any other dev tool we have ever used" It's in Sourcegraph code search now and will be in Amp soon, helping it in megarepo/polyrepos. This is the code search we wanted to build from day 0, and now it's possible!

sqs's tweet image. OH: "Deep Search gets more unsolicited fan mail than any other dev tool we have ever used"

It's in Sourcegraph code search now and will be in Amp soon, helping it in megarepo/polyrepos. This is the code search we wanted to build from day 0, and now it's possible!

Sourcegraph أعاد

Hey Neovim friends, we've got some good news: You can now connect the Amp CLI to Neovim!


Sourcegraph أعاد

Had a great time talking about the evolution of Amp with @adamstac on The Changelog. We discussed the shift from chat LLMs to agents, our ever-evolving list of agentic coding best practices, and I also used the term "cyberspace" at one point, which Adam found very amusing

beyang's tweet image. Had a great time talking about the evolution of Amp with @adamstac on The Changelog. We discussed the shift from chat LLMs to agents, our ever-evolving list of agentic coding best practices, and I also used the term "cyberspace" at one point, which Adam found very amusing

Sourcegraph أعاد

Build Crew Livestream: AI Agent Best Practices and Prompting Strategies 00:00 - Introduction and Build Crew Launch with @ryancarson 02:44 - What is the Build Crew community? 04:08 - @thorstenball's thread: debugging CLI performance with agents 10:17 - Understanding tmux for…


Sourcegraph أعاد

Amp CLI now has custom slash commands. It is a slightly different spin. I did not like the custom syntax on top of Markdown. You can express them in two ways: - Raw Markdown - Executable Executables inject what comes to stdout into the context of the LLM. Write them in any…

nicolaygerold's tweet image. Amp CLI now has custom slash commands. 

It is a slightly different spin. 

I did not like the custom syntax on top of Markdown. You can express them in two ways:
- Raw Markdown
- Executable

Executables inject what comes to stdout into the context of the LLM. Write them in any…

Sourcegraph أعاد

At our latest AI Dev Tools night, @thorstenball gave a presentation on how Amp uses subagents with separate context windows to solve the problem of context window pollution. wtf is context window pollution? > long file contents from reading multiple files > verbose output from…


Sourcegraph أعاد

Impressed by the quality of @AmpCode. Closest I've felt to having an experienced developer available straight in my terminal. Credit card starts bleeding fast as well though. It's a bold move to really just go for best quality vs cost as differentiator.


Sourcegraph أعاد

“Automating software development seemed crazy…Now, it seems obvious.” @Sourcegraph CEO Quinn Slack - @sqs joins NYSE at @theAllinpod’s “Winning The AI Race” in D.C.


Loading...

Something went wrong.


Something went wrong.