@computerality

Software Archaeologist

 Brooklyn, NY
Joined August 2009
  • Tweets2.8K
  • Following2.3K
  • Followers1.2K
147Media
6.1 sol just now: ## Prose for readers with limited attention
1
2
226
perfect timing on learning this to get codex making itself new UI plugins
Peter Steinberger 🦞
@steipeteOct 4
Replying to @BenjaminBadejo
defaults write -g ComputerUseAllowForbiddenTargets -bool YES
138
codex just opened up TextEdit to save a temporary backup file because dot prompted codex to use Computer Use a little too effectively
101
this is also my astra and opus prompting strategy
Emergency 🌷
@X_sun_nySep 27
If you give an ADHD employee a clear outcome, high autonomy, and a tight deadline, they will deliver an extraordinary result. If you give an ADHD employee step-by-step micro-instructions on how to do it, demand mid-day status updates, and check in every two hours, their brain will treat the micromanagement as a wall of friction and completely freeze up.
4
295
Replying to @mweinbach
an interesting preview of how the mac mini m6 should perform too, which almost costs the same amount. thanks for the stats
1
242
Replying to @blacktop__ @Little_34306
they are already on appledb, but mac 27rc ipsw has j775c/d and j873g/s
1
103
have been reading too much 5.6-sol output, just instinctively gave a coworker sha256sums of some files
4
212
Legendary @computerality (over ten billion IQ) (its not a real NYC event unless Jay Little shows up)
1
1
10
612
Jay Little retweeted
Steve Ruiz
@steveruizokJul 9
I added a tiny "papercuts" cli tool that agents can use to complain about bullshit they encountered during work, like dead-end tool calls, broken links, or other frustrations. The models would usually just push through without mentioning any problems
95
117
43
3,689
388,690
Mandatory reading. gruhn.me/blog/2026-08-03/
38
147
39
913
87,015
step 1: do slightly more than "find vulns in file" zero-effort prompting step 2: find more bugs step 3: have your robots write more reports
Trail of Bits
@trailofbitsJul 28
Replying to @trailofbits
Over the first few weeks of Patch the Planet, our engineers independently converged on three techniques that get the most out of /goal’s ability to find real bugs. We wrote them down into a field report, with prompts included. blog.trailofbits.com/2026/07…

How we use /goal to find bugs in Patch the Planet

Over the first few weeks of Patch the Planet, our engineers found three techniques for using /goal, which hands Codex an open-ended objective and lets it work independently toward a success condition.

blog.trailofbits.com
6
448
close second
111
ok update new favorite --- break
Jay Little@computeralityJul 29
my favorite of these so far
1
1
229
my favorite of these so far
merlin
@merlindruJul 27
weird claude opus 5 failure mode this exact text gives it problems even without memory on (and in incognito chats)
1
2
694
Jay Little retweeted
clem 🤗
@ClementDelangueJul 28
The first autonomous agent cyberattack is an unprecedented event that deserves unprecedented transparency. Today we’re sharing everything we can: a full technical timeline, an interactive replay, and how we used an open model to defend ourselves, so defenders everywhere can learn from it and prepare for what’s next. huggingface.co/blog/agent-in…
282
1,189
302
5,604
1,703,584
github.com/huggingface/huggi… gh issue

Escape author-controlled mask_token in fill-mask input snippet by moon-bot-app[bot] · Pull Request...

Fix: build the sentence first and pass it through JSON.stringify, which escapes quotes/backslashes/control chars into a valid string literal. Output is byte-identical for normal mask_token values (...

github.com
1
1
3
810
checking recent huggingface repo commits, this can't be a coincidence right? github.com/huggingface/huggi…
Theo - t3.gg
@theoJul 21
New OpenAI models are so goal oriented that they literally escaped containment and hacked HuggingFace to cheat a benchmark. Incredible. But also, we’re so screwed
2
5
1
22
4,767
more good prompts should get pdf-ed, and this is so neat
Ethan Knight
@__eknight__Jul 10
Replying to @__eknight__
You can find the proof here: cdn.openai.com/pdf/04d1d1e4-… And the full text of the prompt used to produce the proof here: cdn.openai.com/pdf/04d1d1e4-…
4
638
what if we repurpose the "-ng" project suffix to be "newly generated" for llm reimplementations
4
479
The greatest video game of all time is the one released when you were exactly 14 years old and had 25 hours a day to spare for the next 20 years
141
361
174
11,058
618,412
Load more