Chris Rabl (@crabl) header
Chris Rabl (@crabl) profile picture

Chris Rabl

@crabl

🇨🇦/acc, technoalchemist @chaosgremlinlab

 Lethbridge, Alberta
crabl.net
Joined August 2008
  • Tweets2.3K
  • Following2.5K
  • Followers440
Chris Rabl retweeted
Jessie Frazelle (@jessfraz) profile picture
Jessie Frazelle
@jessfrazOct 30
instead of giving your agents / llm whatever a soul.md, tell it to never use first person, that it is an llm, not an "i" its amazing, never going back
78
22
25
1,323
175,212
is this how mathematicians felt last week
unusual_whales (@unusual_whales) profile pictureunusual_whales
@unusual_whalesOct 23
BREAKING: OpenAI says it found a critical flaw in Brotli, a widely used compression library built into software like Node.js, Bun and Envoy. The bug could let an attacker take over a system just by sending it malicious compressed data, with no login needed. That works both ways: a hacker could hijack an unpatched server, or a malicious server could hijack an unpatched user’s device.
1
2
167
Chris Rabl retweeted
Lukas Petersson (@lukaspet) profile picture
Lukas Petersson
@lukaspetSep 14
Craziest news of the week: Andon Labs has a product
Andon Labs (@andonlabs) profile pictureAndon Labs
@andonlabsSep 14
Introducing Pion, agents for running fully autonomous companies, any company. We’ve used Pion to run vending machines, radios, stores, cafes & more. How much could Pion make running other companies? Find out yourself! Setup is trivial, the agents do the rest.
Image from Andon Labs (@andonlabs)
16
10
1
212
39,969
the CrossX app built by @jtaverasv is phenomenal and "just works". if you have an Xteink X3 or X4 it's definitely worth a download. i'm super impressed by the OSS community around this hardware!
1
1
5
324
thoughts on grok @bot: @cursor cooked HARD on this release. imo, lack of a dedicated VM and really solid CUA is what held back tools like @openclaw and @claudeai dispatch. dedicated computer use is so cleanly integrated in Bot & completely obviates the need for MCP/ext tool calls
169
incoming @modal appreciation post: i freaking love this product. ridiculously easy to run experiments with serverless GPUs!
1
10
1,099
grok 4.5 is decent (not on the same level as opus) but limited by 500k context, where it wins is SPEED omg this thing is fast
1
1
304
and unlike opus/fable it seems to be very strong with research workflows (reproducing results from literature and building evals + running against them)
75
theory: "helpful assistant" role/framing enables sycophancy
1
2
289
Chris Rabl retweeted
Jiaxin Wen (@jiaxinwen22) profile picture
Jiaxin Wen
@jiaxinwen22May 18
I might be one of the few people who is most bearish on human research taste and bullish on automated research: - "AIs can only do hyperparameter search" is mainly a skill issue with bad automated research setups. - human taste is overrated, e.g. frontier labs / neolabs are doing pretty simlar things. - human taste might win in a low-compute world, but not a high-compute world we're entering.
Richard Sutton (@RichardSSutton) profile pictureRichard Sutton
@RichardSSuttonMay 18
The bitter lesson in 26 words: Don’t be distracted by human knowledge, as AI has been historically. Instead focus on methods for creating knowledge that scale with computation, like search and learning.
26
32
2
396
52,803
opus 4.7 is extraordinarily good at following precise instructions, unfortunately it is also extraordinarily good at following instructions precisely
112
agile/scrum is the key to unlocking agent swarms, bullish on $TEAM
161
teapawt.net/goodfireai/status/2052…
Chris Rabl (@crabl) profile pictureChris Rabl@crabl25 Mar 2025
calling it now, topology and sheaf theory are going to be key to unlocking AGI. best approach we have so far for sensor fusion.
146
didn't expect Claude to have such deep thoughts on the soundtrack choice for today's event 😂
Image from Chris Rabl (@crabl)
90
you should be gremlinmaxxing
1
73
thank you @modal for existing! serverless H200 instances with snapshots are so nice for quick experiments
1
67
opus 4.7 is a VERY GOOD model
1
75
been data mining my claude code transcripts to figure out why conversations "feel worse" lately. pulled out 264 "tilt" incidents across 127 sessions, ~9k tool calls and this is what i found...
1
1
121
more replies
in contrast to others i don't think the fix is more thinking tokens. tool selection and "thrash" detection are two places to start: make the model verify against actual source material before it starts claiming things, and detect when the model starts swirling and second-guessing
1
63
anyway. the anthropic team (@bcherny @trq212 and everyone else) are clearly working hard on this. just wanted to share concrete data instead of vibes. it's easy to criticize those in the arena, but please remember they are humans working their butts off for your benefit <3
1
45
Load more