Viewing profile — gfosco
gfosco
HN member- Joined
- Wed, Dec 14, 2011, 8:08 PM UTC
- HN karma
- 2,899
- Public activity
- 620 items
- HN profile
- View on Hacker News ↗
About gfosco
Parse -> Facebook 2013-2020, Gab 2020+
fosco at fosco dot com.
Recent public activity
-
comment
Comment #49078833
I have tested this exact scenario, and it works. Opus 5 had access to IDA over MCP, and I simply asked it HOW certain things were done in the target binary. Purely informational, e…
-
comment
Comment #47978045
I didn't feel like installing a whole redis-server service on my Windows machine, so instead I built a lightweight yet very capable clone. Maybe you'll find it handy for local deve…
- story
-
comment
Comment #47871338
I set this up today on my 5090 at Q6_K quantization and Q4_0 KV, got 50 tokens/s consistently at 123k context, using ~28/32gb vram through LM Studio.
-
comment
Comment #47787617
Yeah, it's token intensive but worth it. I built a very dumb example harness which used IDA via MCP and analyzed/renamed/commented all ~67k functions in a binary, using Claude Haik…
-
comment
Comment #47610031
No you fell for someone elses joke.
-
comment
Comment #43051822
Somehow not surprising to see this take on the front page. How embarrassing.
-
comment
Comment #41417197
I remember being an early teenager on IRC and joining a small BBS development team. I said I knew Pascal, but that was a fib... I did learn it quickly, though, and used it for many…
-
comment
Comment #41343153
[flagged]
-
comment
Comment #40900357
Same here... It's still amazing, and I have no legitimate reason to upgrade. Could be looked at as a failure of some sort, that they haven't given us a good reason.
-
comment
Comment #40899183
Not mentioned in the article, but one major provider for this is AskSage.ai, which has built up a lot of features around creating government documents, proposals, RFPs, etc.
-
comment
Comment #40690775
Depends who you ask. To me, NDT is unbearable too...
-
comment
Comment #40690755
Not by themselves... but with a good program built around it, managing the actual state, and very careful prompting, yes. I've been thinking about this for a while, always have the…
-
comment
Comment #40665553
Looking to get rid of a few?....
-
comment
Comment #40637168
The OpenAI reference came at the end, and it appears it's mostly a fallback... an option, that users must explicitly allow every time. Hardly a dependency. Most of the time, it wil…
-
comment
Comment #39731848
At the end of the article, that's my takeaway too. I can't imagine going to this level of effort on the Vision Pro and not keeping it to see how the software develops.
-
comment
Comment #39637114
It is extremely silly to think using Gab AI says anything about you, except you want good AI that isn't ruined. Extremely silly.
-
comment
Comment #39637021
You really don't have to talk to Hitler, there are 200+ other characters to choose from... and no, I don't think there is a middle ground when it comes to censorship. Either all le…
-
comment
Comment #39636480
If you want uncensored.. https://gab.ai is also comparing well with gpt4.
-
comment
Comment #39621617
I have the Bambu Lab X1C with the AMS and I'm chomping at the bit to get a second AMS and the Hub... If they weren't backordered I would have already. I've had machines from Type A…
-
comment
Comment #39231996
You think a font being a few tenths of a millimeter off spec is a "dangerous defect" ? Let me guess... not a fan of Elon.
-
comment
Comment #39231731
Perhaps it's time to fight over words. The definition of recall no longer works, and I believe it is constantly used specifically negatively against Tesla. It has an effect on most…
-
comment
Comment #38862619
It's always worth it... Sometimes, even the downvotes are enjoyable.
-
comment
Comment #38353104
WSG, Windows Subsystem for GPT
-
comment
Comment #36925431
[flagged]