Infinite context. Never compact. Local-first AI coding agent. Use your existing Grok / OpenAI subscription or BYOK. Free.
Joined July 2026
- Tweets2.1K
- Following994
- Followers213
- Likes1.9K
Manna Code retweeted
HOLY COW
I cannot believe this is real.
Everything we told you about vouching in Minnesota is correct.
“A registered voter in that precinct who can personally vouch for the identity & residence of up to 8 new voters.”
“A healthcare facility worker can vouch for an 👉UNLIMITED👈 number of residents of facilities that they work for
regardless of where that facility worker lives.”
This is from an Election Judge training video for Carver County, Minnesota.
Manna Code retweeted
Minnesota allows foreign t*rrorists to vote without ID as long as someone “vouches” for them
This is literally one of the nost insane things ever
How is this happening in our country?!
No words
BREAKING: Hidden camera captures Minnesota poll workers confirming alleged foreign terror organization members can vote if vouched for.
We put Minnesota’s voter “vouching” system to an extreme test by asking if it was okay to vouch for alleged Hamas militants who had recently come to America from the Gaza Strip.
An election worker said, “You can vouch for up to 8 people,” and added, “If you’re vouching for them, they wouldn’t need to show anything,” referring to the alleged Hamas members we asked about registering to vote.
We were also told that the person doing the vouching “is the documentation.”
Minnesota Secretary of State @MNSteveSimon continues to claim the vouching system is safe and secure. Our investigation shows the opposite.
We are calling for a formal audit of Minnesota’s voter vouching system.
This report was produced in partnership with @ctznjusticelg
Manna Code retweeted
astra is a powerful model and we are working to make it generally available.
we do not think it is a good strategy to keep powerful models to a chosen few.
given its cyber capabilities, we need a little big longer to do do this safely. but hopefully not too long!
Manna Code retweeted
Any serious, functioning state would:
IMMEDIATELY deploy the army, shut the invasion down with all force necessary, round up every invader, send them all back, sever diplomatic ties with Morocco and impose severe sanctions and restrictions.
Show some fucking balls and loyalty to your own people, for once.
Instead, our traitorous politicians TWEET.
Manna Code retweeted
The United States stands with the people of Spain, and all Europeans, against this egregious violation of their sovereignty and human rights.
This unacceptable incident is the direct result of the Spanish Government's deliberate efforts to enable and facilitate mass illegal migration into Europe.
We are considering actions to defend Americans at home and abroad from this threat and stand ready to assist other European allies considering similar options.
Manna Code retweeted
Now that our border is locked down, it's easy for people to forget what the chaos under Democrats actually looked like.
Republicans should run comparison videos with the Spain invasion on a loop until November.
Manna Code retweeted
Install the open-source Codex Security CLI,:
npm install @OpenAI/codex-security
Or start with:
npx @OpenAI/codex-security@latest --help
NPM: npmjs.com/package/@openai/co…
Manna Code retweeted
We quietly released the open-source Codex Security CLI, but Hacker News found it before we had a chance to share it here...
You can now use it to scan repositories, track findings across runs, verify fixes, and add security checks to CI/CD.
This is an early release, and we're listening to your feedback as we continue improving it.
Manna Code retweeted
A new app idea called Linked-Out where people can post about why they left their toxic workplace.
Manna Code retweeted
Anthropic had the biggest miscalculation in AI 2026:
1. They underestimated the progress others made, and thought they can win forever.
2. Thus, they assumed their customers will continue to tolerate their terrible policies (pricing, random usage limits, bad data retention, arbitrary access removal etc.) and cocky PR because they are AGI. They didn't invest in building customer trust because they thought they didn't need to.
3. They also assumed by simply painting open-weight as dangerous and unsafe, they can persuade enterprises to not touch them and persuade government to ban them.
4. They knew user data in Claude Code is how they win, yet their bad user policy/pricing gave aways their already-sticky users to Codex/Grok/etc, enabling others to capture equally valuable user data on their own.
5. Meanwhile, they didn't invest enough in owning their compute, instead putting itself in a vulnerable position at the mercy of @elonmusk, their competitor.
When a strong open-weight provider catches up(@thinkymachines, Kimi, GLM etc.), people suddenly realized Claude has 1. no pricing advantage 2. no compute advantage 3. no branding advantage (already broke enterprise trust, pissed off prosumers, and consumers don't know Claude exists)
Anthropic needs some serious strategy pivots. The status quo won't work at all for them. They still have the highest caliber talents, so I am still hopefully they will change for the better. But simply a better model than Fable isn't going to be enough to turn things around IMO.
Manna Code retweeted
Kimi K3 just fixed 15 critical security bugs that Codex and Fable refused because of “cyber guardrails.” There’s no reason to limit American models on tasks that Chinese models handle without issue. We’re only making ourselves less competitive.
Manna Code retweeted
absolutely incredible things happening on the TL:
alibaba effectively admitted to being MANDATED by their Big Guy to pivot AWAY from closed and TOWARDS open (weights)
while the US is throwing export controls around like a game of blind pin-the-tail-on-the-donkey, China is really going all in on commoditization, forcing their corps to foot their own AI bills and release the final artifacts to the public (thereby controlling public fear of walled gardens and mass job displacement while allowing their AI labs to build goodwill at the same time)
now tell me, who is the blind one in their policy strategies?
