RT @nicolaygerold: Amp CLI now has custom slash commands. It is a slightly different spin. I did not like the custom syntax on top of M….

Raising An Agent - Episode 8. In this episode, @beyang sits down with @camden_cheek to discuss how the Amp team evaluates new models: why tool calling is the key differentiator, how open models like K2 and Qwen stack up, what GPT-5 changes, and how qualitative “vibe checks” often

Join millions who have switched to Grok.

RT @umpox: Amp Tab now lets you Tab through multiple files:

Amp CLI can now read diagnostics from JetBrains IDEs for JVM languages such as Java, Kotlin, and Scala.

RT @sqs: Today we followed through on a commitment made on May 17: @AmpCode would switch to AGENTS not AGENT dot md if OpenAI could get the….

RT @thorstenball: Okay, this was pretty magical. I was debugging an issue, hand-in-hand with the main agent: adding logs, trying stuff, as….

RT @thorstenball: Latest on GPT-5 in Amp, by @camden_cheek

RT @lewis_b_metcalf: Amp CLI now has `/new` and `/continue` slash commands

RT @sqs: Amp can now use 432,000 tokens of context: longer threads, more iterations, and more replies.

RT @connorado: At our latest AI Dev Tools night, @thorstenball gave a presentation on how Amp uses subagents with separate context windows….

RT @_dhamidi: Amp now has a better permission system. You can now define exactly which tool (built-in or MCP) can run with which arguments….

RT @thorstenball: New JetBrains integration in the Amp CLI

RT @thorstenball: There it is, the first orb

RT @ryancarson: I'm thrilled to announce that today I'm joining @ampcode as Builder in Residence. The journey here started all the way bac….

RT @SagtaniHitesh: Amp Tab is now 30% faster. We worked with Baseten to switch to TensorRT-LLM and KV caching with speculative decoding.….

RT @tema_codes: Just shipped thread forking for @AmpCode

Amp's CLI now has -x