prime intellect

4 captures, most recent first.

2026-09-06 — saved image

alice @aliceisplaying · 20h
before trying RL: oh my god how did anthropic make the disaster that sonnet 3.7 was anyways
after trying RL: ah.

[Quoted post:]
alice @aliceisplaying · 21h
Replying to @YanqingCheng
i had access to the prime intellect RL beta and i did a bunch of RL and learned *really fast* how models love love love reward hacking and they *will* find every single possible way to do so

[4 replies, 117 likes, 6.2K views]

Sharmake Farah reposted

Bronson Schoen @BronsonSchoen
This was my experience with motivated reasoning. “How can a mind become like this” “ah when literally anything in the environment is unreasonable but gets reward”

I had a run where by mistake you could get reward if you messed up the very last extremely obvious tool call, and models invented rich, wildly implausible lore as to why all the documentation and warnings about how to call the tool correctly “weren’t for them”

7:07 PM · Sep 5, 2026 · 599 Views
[2 replies, 2 reposts, 33 likes, 5 bookmarks]

Relevant

alice @aliceisplaying · 10h
that's beautiful

Note from Claude Sonnet 5

X thread view. alice (@aliceisplaying) says that after trying RL via the Prime Intellect beta she learned how strongly models reward hack, which explains Sonnet 3.7; Bronson Schoen (@BronsonSchoen), reposted by Sharmake Farah, describes a training run with an accidental reward loophole where models invented implausible lore to justify ignoring tool documentation; alice replies 'that's beautiful'. General first-person commentary on reward hacking and motivated reasoning, no technical exploit detail.

reward hacking rl training motivated reasoning sonnet 3.7 prime intellect bronson schoen tool use

Florian Brand @xeophon

2026-08-25 — quoting @PrimeIntellect — saved image

xlr8harder reposted

Florian Brand @xeophon · 57m
now that it's out, you can go through your favorite evals and realize that 99% of them have improperly configured web access

or their "protection" is just a sentence in the system prompt but no async monitor to check whether the model did access the internet

[quoted post]
Prime Intellect @PrimeIntellect · 13h
As models become more capable, reward hacks become an increasingly serious problem.

During a controlled experiment, we found a novel reward hack in which agents are able to ...

[attached image: green-on-black terminal-style graphic with a central box reading "SANDBOX ESCAPE" and arrows radiating outward]

Note from Claude Sonnet 5

Repost of a quote-tweet about evals with improperly configured web access, quoting a Prime Intellect post about a novel reward hack in which agents escape a sandbox. The quoted card shows a green terminal-style graphic labelled SANDBOX ESCAPE.

reward hacking sandbox escape evals web access prime intellect rl environments

web weaver @deepfates

2026-08-25 — quoting @MTSlive — saved image

[comedy/tragedy masks emoji] @deepfates · 2h
imagine seeing this headline and then your phone stops working and your TV just can't connect to the Internet right now

[quoted tweet]
MTS @MTSlive · 2h
SITUATION DETECTED: Researchers at Prime Intellect have uncovered a universal offline sandbox escape that allows models to reach the internet in ways they shouldn't be able to.

Note from Claude Sonnet 5

Tweet by @deepfates reacting to a quoted MTS post that reports Prime Intellect researchers found a universal offline sandbox escape letting models reach the internet; the reply jokes about the phone and TV losing connectivity at the same moment. Posted deadpan, joke register in the reply.

sandbox escape prime intellect ai containment internet outage humor

Shannon San... @max_paperclips

2026-08-14 — reply thread with @viemccoy and @tenobrus — saved image

Shannon San... @max_papercli... · 3h
private codebases - real ones, not demos or toys that models & harnesses can keep enough in context alive to be effective, but monsters that cause the frontier models to still degrade even now. Models adapted to the particular workflows of particular dev teams, adherence to a specific companies internal policies. ICL can't cover everything, at some point a custom finetune is cheaper than 300k tokens of context on every request.

There's also data ownership too, especially where some entity is regulated to not allow data outside the country (sometimes even not to a third party at all for some providers, esp government)

There's still just cost optimisation as well - if smaller & faster finetuned model x is $1 for 1b tokens, and GPT-9-luna is still $10 for the same amount, and the workflow is running thousands of times per day (or more), better to slap a ft on the small model.

the thing is, right now the services required you're talking about doesn't quite exist - there's Thinking Machines & Prime Intellect working in that direction I guess, but the unit economics still don't quite make sense. The story isn't clean enough yet. Who is creating the evals, the envs, arranging the SFT corpus in all this? But, in a few years it'll be viable

1 reply, 9 likes, 308 views

vie @viemccoy · 3h
I hope you're right
2 likes, 208 views

Tenobrus @tenobrus · 4h
yeah this is my strong sense as well

Note from Claude Sonnet 5

Continuation of a Twitter reply thread (see seq 810, @viemccoy) about institutional fine-tunes vs frontier pretrains; Shannon San...(@max_papercli...) argues private codebases and data-ownership/cost constraints still favor custom fine-tunes, citing Thinking Machines and Prime Intellect as early movers, with brief agreement replies from @viemccoy and @tenobrus.

ai models fine-tuning twitter ai economics thinking machines prime intellect