@drnafizhamid @AmpCode This was a regression that went out today and will be fixed on the next version update. Sorry about the confusion and thanks for flagging!
English
Beyang
6.8K posts
Beyang
@beyang
Building @ampcode @sourcegraph
San Francisco, CA Katılım Eylül 2008
1.9K Takip Edilen12K Takipçiler
Note on GPT 5.5's data retention requirements, which appear to apply broadly to agents using this model. If you're willing to waive ZDR (zero data retention) by OpenAI, you can use it in Amp with these instructions.
(Still no training on this data, even w/o ZDR, in Amp)
Quinn Slack@sqs
You can use OpenAI GPT-5.5 in Amp's deep mode with this in ~/.config/amp/settings.json: { "amp.internal.model": { "deep": "openai:gpt-5.5" } } Will be the default soon. Why not yet? Because... For now, usage of GPT-5.5 uses OpenAI's Safety Retention Policy, which means non-zero data retention by OpenAI in the (~0.05%) case of inputs that OpenAI's classifier identifies as severe cybersecurity abuse risk. We're working with OpenAI to lift this requirement, which as far as we know applies to use of GPT-5.5 in other agents as well. (Has anyone seen this disclosure from other agents?)
English
We raised a Series A for exe.dev. We are going to build a new cloud. blog.exe.dev/series-a
English
Wow this looks slick!
Rach@rachpradhan
We built the fastest browser automation stack for AI agents.. 464 KB, 3ms cold start, 16% cheaper per agent loop than anything else out there. Here's how it started and why it exists. Shoutout to @AmpCode for the credits for the initial start of this project!
English
@beyang this feels good to see as outside too. there's hope
English
We've switched deep mode in Amp over to GPT-5.4. Should be less verbose than stock 5.4 in other settings. I've been using this as my main agent for the past couple weeks or so and it's great.
Nicolay Gerold@nicolaygerold
GPT-5.4 now powers Amp’s deep mode. Out of the box it talked too much for what we want, so we tuned it to act more like Codex: a model that goes off, reads, thinks, and comes back with work done. Try deep^3. Or deep if you’re feeling impatient.
English
@sauercrowd @SuryavirKapur Hmm, I’ve never had this issue with any of the M* Macs, including an M3 MacBook with 16g RAM. They’ve all been instant wake and snappy. Maybe you have SSD corruption or something 🤷♂️
English
@beyang @SuryavirKapur battery life - totally - but performance I can't say my macbook pro is particularly amazing. The OS just accumulates so much stuff so quickly.
If the lid's closed and I want to jump on a call and open it, takes like 30s to collect itself before I can join the call.
English
@SuryavirKapur @sauercrowd Many reasons but mainly battery life and performance of Mac hardware.
English
@sauercrowd Longtime user. Tiling window manager that was simple but configurable
English
@beyang what led you to i3 originally (as in, away from default wm)? or were you already a long term user?
English
@sauercrowd i3 - highly customized
i3 - almost stock
Aerospace (switched to Mac for $REASONS)
Now mostly stock macOS window manager (but have toggled between same workspace across screens to individual screen workspaces)
English
@beyang I can definitely be more active in discord 😅 and it looks like I got to pump up my numbers at work and on my personal account 😏
English
Congrats to Linear on the bold pivot. If you want to figure out what the future looks like, you have to get close to the code.
Cristina Cordova@cjc
Issue tracking is dead. 🪦 We’ve been trapped in a handoff model where process became the work and engineering time was wasted on ceremony. That era is over. Today, we’re launching the Linear Agent, Skills and Automations. The future is execution, not overhead: linear.app/next
English
@ivanleomk @GoogleDeepMind @OfficialLoganK @thorwebdev @DynamicWebPaige @_philschmid @patloeber @ammaar @vadiamit @osanseviero @harrisonfjobe @goodside @alihcevik @matthewridenour Welcome! Let's grab lunch or coffee sometime!
English
Life update I’ve moved to San Francisco and joined @GoogleDeepMind.
Excited to work alongside @OfficialLoganK @thorwebdev @DynamicWebPaige @_philschmid @patloeber @ammaar @vadiamit @osanseviero @harrisonfjobe @goodside @alihcevik @matthewridenour
English
@aaronluannguyen Use Amp, give feedback (best way is to join our Discord). Future is already in the hands of some power users!
English
@beyang Any way I can participate in amp's version of the future where "the coding agent is dead" 😉
English