Joe Palermo Profile
Joe Palermo

@joepalerm0

Followers
1K
Following
638
Media
2
Statuses
85

Machine learning engineer from Toronto; Member of Technical Staff @OpenAI

Joined December 2013
Don't wanna be here? Send us removal request.
@joepalerm0
Joe Palermo
7 months
Reinforcement finetuning is just one of several strategies we're pursuing to make AI more useful in industry.
@aleks_madry
Aleksander Madry
7 months
If AGI is about AI transforming our economy—how close are we, really? What's still missing, and how do we get there? OpenAI's new Strategic Deployment team tackles exactly these questions. We push frontier models to be more capable, reliable, and aligned—then deploy them to
0
0
10
@joepalerm0
Joe Palermo
8 months
We’ve been hard at work on reinforcement fine-tuning (RFT) to make it a more flexible and powerful tool. RFT is best thought of as a way to improve model capabilities on well-specified tasks with known correct answers. It shouldn't come as a surprise that models can often get
@getsafetykit
SafetyKit
8 months
We worked with the @OpenAI  team to test and evaluate fine-tuned reasoning models in SafetyKit and saw great results, especially with complex instruction following and large context windows. SafetyKit customers need lots of expert-level decision-making across lots of complex
2
12
59
@joepalerm0
Joe Palermo
2 years
"The models just want to learn" -Ilya Sutskever
@agihouse_org
AGI House
2 years
Joe Palermo (@joepalerm0 - research engineer @OpenAI) talking about "Customizing GPT-4" at our inaugural AGI House hackathon @ MIT
4
4
32
@ericschmidt
Eric Schmidt
2 years
David Deutsch: "We have a duty to be optimistic. Because the future is open, not predetermined and therefore cannot just be accepted: we are all responsible for what it holds. Thus it is our duty to fight for a better world."
43
156
819
@joepalerm0
Joe Palermo
2 years
Computers are great for reversing local entropy. For a start what I want is: 1) A robot to follow me around and cleanup my messes, 2) A brain-computer interface to remember all the things I forget, 3) Nanobots in my body to repair cellular damage.
2
1
17
@joepalerm0
Joe Palermo
2 years
The overwhelming feeling is of love for each other, commitment to our mission and the absolutely indomitable will of the OpenAI team.
3
3
44
@joepalerm0
Joe Palermo
2 years
OpenAI is nothing without its people
4
12
270
@joepalerm0
Joe Palermo
3 years
Fun with the system message on GPT-4.
16
31
320
@jackclarkSF
Jack Clark
3 years
One like = one spicy take about AI policy.
46
318
3K
@nick_slaney
Nick Slaney
3 years
Interested in designing and building lightning infrastructure for the next billion lightning users? 👇 https://t.co/y7n809e4sM
@nick_slaney
Nick Slaney
3 years
To that end, I’ve been very lucky to connect with a lot of great Lightning-minded folks on Twitter. We’ll be posting jobs for this initiative in the near future. If you’re an engineer who has been looking to get into Lightning professionally this could be a great opportunity.
1
4
10
@balajis
Balaji
7 years
Open state databases are the next step after open source software. They are databases anyone can read from (for free) or write to (for a price), with incentives and algorithms set up to prevent corruption. You might also call them distributed ledgers :)
@balajis
Balaji
7 years
Blockchains are the next step after open source, as they provide open data & open execution. You don’t just see the source code with something like Bitcoin or Ethereum. With a full node you see all historical data, all pending writes, and can retrace every step of code execution.
28
187
855
@_akhaliq
AK
4 years
Efficient-VDVAE: Less is more abs: https://t.co/uNtYzgHHAj github: https://t.co/kJNbAKJ0I8 simple modifications to the Very Deep VAE to make it converge up to 2.6× faster, save up to 20× in memory load and improve stability during training
0
29
133
@balajis
Balaji
4 years
It is obvious that the current angel investing system — Docusigns and Hellosigns, Clerkys and Cartas, contracts and valuations, emails and wires — will all go on-chain. Every aspect is simplified if you can simply send USDC to an ENS address and get digital assets back.
89
225
2K
@SinghJyotirmai
Jyotirmai Singh
4 years
This extract from @balajis excellently summarises the main reason why I started my science newsletter Those of us on the front lines of science need to educate the public on all the amazing research going on today & if possible inspire the next generation 🙏
6
24
258
@joepalerm0
Joe Palermo
4 years
Any chance we can move this 🇨🇦 debate for the Fernandez match??
0
0
0
@brockm
Mike Brock🇺🇸
4 years
Say what you want about @elonmusk, but between @Tesla and @SpaceX, it's hard for me to think of another person alive today that is bending the trajectory of humanity towards a more positive future at the scale he is. Our political leaders certainly aren't these days.
324
1K
9K
@joepalerm0
Joe Palermo
4 years
Much work remains to be done but we believe that program synthesis will become increasingly important in the quest to build AI capable of reasoning from limited data.
0
0
2
@joepalerm0
Joe Palermo
4 years
See our repo for a visual depiction of the environment:
github.com
Contribute to JohnnyYeeee/math_prog_synth_env development by creating an account on GitHub.
1
0
0
@joepalerm0
Joe Palermo
4 years
Each action taken in the environment adds an operator or an input into a discrete compute graph. Graphs which compute correct answers yield positive reward, enabling the optimization of a policy to construct compute graphs conditioned on problem statements.
1
0
0