Brecht De Rooms

2.1K posts

Brecht De Rooms banner
Brecht De Rooms

Brecht De Rooms

@databrecht

👩‍💻 with a special place in his heart for tech, design. 🎸@ Ethereal Darkness (doomy melodic 💀)

Belgium शामिल हुए Ekim 2019
342 फ़ॉलोइंग462 फ़ॉलोवर्स
Brecht De Rooms
Brecht De Rooms@databrecht·
This hardly seems like a fair comparison since this adds extra loops? Would others not score better as well if they ralph wiggum it?
Kangwook Lee@Kangwook_Lee

We got 74.4% on TerminalBench2 with Opus 4.6 simply by improving Terminus 2. That's up from 62.9% on "Terminus 2 + Opus 4.6", making Opus 4.6 match "Simple Codex + GPT-5.3-Codex". We'll share a short technical blog post + open-source the modified Terminus soon. Stay tuned 😉

English
1
0
0
499
Brecht De Rooms
Brecht De Rooms@databrecht·
@tessl_io "Viktor has volunteered (he doesn’t know this yet) to package OpenSpec as a Tessl tile too, since he loves it so much. One registry, one install command, all your agent context." Time to tell Viktor, I'll be happy to see it coming: tessl.io/blog/my-coding…
English
0
0
0
42
Carl Vellotti 🥞
Carl Vellotti 🥞@carlvellotti·
One of my most useful Claude Code commands /lock-in Claude starts an internet blocker called Freedom with a script to click stuff in the menu bar Remember: Claude Code can basically do anything on your computer, just ask
English
12
10
113
18K
Brecht De Rooms
Brecht De Rooms@databrecht·
Not sure how I feel about such features when Claude Code is running behind other terminal agents in terms of prompting/compression/UX (terminal bench). Yet lock us into Claude Code by banning users of Opencode or Droid, and what do they give us? This, how ironic can it be 😁
Daniel San@dani_avila7

Claude Code 2.1.23 is out! This update adds support for customizing the Spinner words, so you can choose what shows up while Claude is working To enable it, add this to your settings.json: "spinnerVerbs": { "mode": "replace", "verbs": [ "Daniel Thinking", "Avila VibeCoding", "Daniel Architecting" ] } Check out my Avila VibeCoding spinner 😎

English
0
0
0
64
Monk Zero
Monk Zero@NoCommas·
this has been the vision of @antigma_labs since day 0. Also we don't compromise performance😘 We constantly top terminal bench leaderboard with our soon to be released agent Ante ~
Will@WClemente

After using Claude code for the first time and seeing how easy it is, it seems pretty clear that the next wave of adoption in AI will be locally hosted agents that automate numerous tasks for you and turn your device into more or less a terminal of agents working for you

English
1
1
6
497
Brecht De Rooms
Brecht De Rooms@databrecht·
@antigma_labs Interested to see how you rank with Opus. Terminal Bench is a good reference, but in the end, for complex architecture: Opus is still king. I'm sure many of us are interested only if it's not tuned towards models that only score good on the smaller Terminal Bench tests.
English
0
0
0
14
Antigma
Antigma@antigma_labs·
Finally got to try Terminal Bench 2.0 with Harbor, and we're on top of the leaderboard again—this time Verified. We built an eval pipeline to streamline the process and make it as transparent and verifiable as possible. This trial spanned 2025 and 2026.
Antigma tweet media
English
3
1
13
510
Brecht De Rooms
Brecht De Rooms@databrecht·
@thdxr Skills are unreliable in every tool I've tested. I'd greatly appreciate a terminal tool who would say: "we don't do skills" instead of adding whistles and bells that simply don't work anyway since these whistles make you lose time. If skills need to be tagged, they are command.
English
0
0
0
10
dax
dax@thdxr·
do skills ever get automatically loaded does this actually work for you?
English
303
8
640
107.6K
Brecht De Rooms
Brecht De Rooms@databrecht·
Meanwhile, people are using things like Ralph happily without problems yet I get banned for using Claude properly, without explanation. @claudeai
English
0
0
0
38
Brecht De Rooms
Brecht De Rooms@databrecht·
@claudeai Might want to identify and fix your issue with banning paying users without providing reasons.
English
0
0
0
8
Claude
Claude@claudeai·
Update: we've identified and fixed an issue with our usage promotion for Max 5x users. We've reset the usage limits for all affected accounts.
English
35
7
273
80K
Claude
Claude@claudeai·
Starting at midnight PT tonight, all Pro and Max plans have 2x their usual usage limits through New Year's Eve.
English
489
590
7.7K
1.6M
Brecht De Rooms
Brecht De Rooms@databrecht·
@claudeai Might want to unban your paying users first who got banned without proper reason.
English
0
0
0
14
Claude
Claude@claudeai·
Claude can now securely connect to your health data. Four new integrations are now available in beta: Apple Health (iOS), Health Connect (Android), HealthEx, and Function Health.
English
382
545
9.8K
1.2M
Brecht De Rooms
Brecht De Rooms@databrecht·
These "it does everything for me automagically" posts are getting tiring. No it doesn't. Worktrees are the sane way to use agents, yes. Planning is the most important step now (like before, but obvious now). Not touching terminals/editors or don't review => fail later on.
English
0
0
0
18
Brecht De Rooms
Brecht De Rooms@databrecht·
@sandip_wane_ @trq212 They refunded me (not sure if the whole amount they owe me) without any additional details, no explanation, absolutely nothing.
English
0
0
1
64
Sandip Wane
Sandip Wane@sandipwayne·
@databrecht @trq212 Has this been resolved on your side, or is there a known workaround? Were you able to reach out to Anthropic Support?
English
1
0
0
31
Sandip Wane
Sandip Wane@sandipwayne·
@trq212 Our Claude account was blocked after an automated review without a clear reason. This has happened before, and despite reaching out to Anthropic support, we did not receive a clear explanation or resolution. We still do not know what activity is being flagged as suspicious, and this is blocking active work. Any help would be appreciated.
Sandip Wane tweet media
English
1
2
0
132
Brecht De Rooms
Brecht De Rooms@databrecht·
@nearcyan that looks incredibl.... ...y non-efficient? But I assume fun.
English
0
0
0
18
near
near@nearcyan·
this is how i claude code now. it's fun!
English
402
573
9.7K
1.5M
Brecht De Rooms
Brecht De Rooms@databrecht·
Same here, no idea why, anyone else?
Leo Alt@leonardoalt

So @AnthropicAI is now randomly banning accounts? Just started getting "This organization has been disabled", without any warning or explanation. Payment is of course processed. Support is 100% useless.

English
0
0
0
19
Leo Alt
Leo Alt@leonardoalt·
So @AnthropicAI is now randomly banning accounts? Just started getting "This organization has been disabled", without any warning or explanation. Payment is of course processed. Support is 100% useless.
English
3
1
11
1.1K
Bumblebee
Bumblebee@0xBumblebee·
@icobeast sadly I got banned on Claude
English
1
0
1
42
Brecht De Rooms
Brecht De Rooms@databrecht·
Dear @NeuralDSP, I love your products but if you obligate cloud usage in the chain, fix your UI! - Clicking one download button results in these calls, no wonder you can't handle load. - I bought amp captures, can't even get an overview as the continuous scroll does not work.
Brecht De Rooms tweet media
English
0
0
0
19

खोजें

@tessl_io @carlvellotti @NoCommas @antigma_labs @thdxr @claudeai @trq212 @elonmusk